© 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. 29204
    Prev
    Next
    INDEX
    Explanations

    terms and identifiers related to programming and data structure definitions

    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
    156
    +0.26
    1.5%
    181
    +0.16
    0.9%
    39
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.26
    0.12
    95
    +0.16
    0.09
    129
    +0.14
    0.03
    Negative Logits
    ?”
    -1.96
    ?’
    -1.62
    ?).
    -1.57
    acial
    -1.48
    orting
    -1.46
    ?",
    -1.44
    ?)
    -1.44
    âĢ¦”
    -1.40
    orts
    -1.38
     "</
    -1.38
    POSITIVE LOGITS
     Equipment
    1.69
    Marshal
    1.66
     Engine
    1.59
    etable
    1.52
    eLife
    1.49
     Marshal
    1.48
     League
    1.46
     Stats
    1.43
     Mode
    1.43
     Controller
    1.42
    Activations Density 1.299%

    No Known Activations