© 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. 4-RES-SM
    11. 10309
    Prev
    Next
    INDEX
    Explanations

    technical programming and software development concepts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    7
    +0.11
    0.6%
    411
    +0.11
    0.6%
    117
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.11
    0.00
    311
    +0.11
    0.03
    490
    +0.10
    0.02
    Negative Logits
     Ai
    -1.68
    eria
    -1.53
    izumab
    -1.47
     Baghdad
    -1.45
    atas
    -1.44
     Io
    -1.41
    ientes
    -1.41
     Faith
    -1.35
    ird
    -1.35
    olev
    -1.35
    POSITIVE LOGITS
     Sw
    3.52
     Sl
    3.11
     SW
    3.02
    SW
    3.00
    Sw
    2.97
     SL
    2.80
    Sl
    2.66
     swap
    2.59
     sw
    2.46
    sw
    2.38
    Activations Density 0.675%

    No Known Activations