© 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. 13638
    Prev
    Next
    INDEX
    Explanations

    references to previews

    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
    235
    +0.15
    0.9%
    154
    +0.12
    0.7%
    284
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.15
    0.03
    154
    +0.12
    0.03
    437
    +0.12
    0.03
    Negative Logits
    unnumbered
    -2.06
    IENT
    -1.88
    hips
    -1.83
    tons
    -1.79
     sake
    -1.75
    hip
    -1.61
    ded
    -1.57
    pread
    -1.56
    iginally
    -1.54
    ging
    -1.51
    POSITIVE LOGITS
    valence
    2.82
    viously
    2.16
    fecture
    2.14
    »
    2.11
    paring
    2.09
    cursors
    2.07
    cursor
    2.07
    ferences
    2.07
    requ
    1.97
    ferentially
    1.95
    Activations Density 0.056%

    No Known Activations