© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25383
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.18
    1.1%
    230
    +0.13
    0.8%
    354
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.18
    0.11
    119
    +0.13
    0.08
    230
    +0.11
    0.09
    Negative Logits
     (“
    -1.90
    .“
    -1.73
    ():
    -1.72
    ł
    -1.68
    .:
    -1.67
    .*]{},
    -1.54
    :&
    -1.50
    .’
    -1.49
    ï¼ļ
    -1.49
    .
    -1.44
    POSITIVE LOGITS
    -------------------------------------------------------
    1.69
    ----------------------------------------------------
    1.66
    ================================================
    1.61
    -----------------------------------------------
    1.59
    --------------------------------------------------
    1.58
    rake
    1.55
    "?"
    1.55
    -------------------------------------------------
    1.53
    ––––––––
    1.52
    ----------------------------------------------
    1.49
    Activations Density 0.912%

    No Known Activations