© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8573
    Prev
    Next
    INDEX
    Explanations

    phrases related to accessibility and ease of use

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.14
    0.8%
    148
    +0.12
    0.7%
    453
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.14
    0.03
    263
    +0.12
    0.03
    102
    +0.12
    0.03
    Negative Logits
    à°¿
    -1.99
    icism
    -1.63
    à±
    -1.59
    tle
    -1.58
    smallcaps
    -1.56
    arean
    -1.56
    à±į
    -1.55
    alia
    -1.53
    typeof
    -1.52
    à±ģ
    -1.51
    POSITIVE LOGITS
     accessible
    2.47
     identifiable
    2.22
     recognizable
    2.09
     accessed
    2.02
     understandable
    1.98
     distinguishable
    1.94
     removable
    1.86
     detectable
    1.81
     obtain
    1.80
    accessible
    1.77
    Activations Density 0.165%

    No Known Activations