© 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. 24839
    Prev
    Next
    INDEX
    Explanations

    paths and file directories

    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
    369
    +0.15
    0.8%
    436
    +0.12
    0.7%
    510
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.15
    0.07
    436
    +0.12
    0.06
    369
    +0.11
    0.03
    Negative Logits
     habit
    -1.94
    zyk
    -1.80
    ypse
    -1.59
    ocytosis
    -1.52
    icity
    -1.51
     conduct
    -1.51
    chitz
    -1.51
    heit
    -1.49
     actu
    -1.48
    yla
    -1.46
    POSITIVE LOGITS
     edition
    1.76
    directory
    1.72
     rpm
    1.68
    rpm
    1.67
    rah
    1.65
    ram
    1.60
    filename
    1.56
    root
    1.47
    80211
    1.47
     editions
    1.42
    Activations Density 0.630%

    No Known Activations