© 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. 15129
    Prev
    Next
    INDEX
    Explanations

    words related to communication or commentary

    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
    489
    +0.13
    0.7%
    380
    +0.12
    0.7%
    435
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.13
    0.04
    380
    +0.12
    0.03
    113
    +0.11
    0.03
    Negative Logits
     courts
    -1.73
    wards
    -1.64
     likelihood
    -1.62
     age
    -1.51
     guard
    -1.51
    oslav
    -1.42
    apine
    -1.42
     tendency
    -1.39
     like
    -1.37
     BASIS
    -1.36
    POSITIVE LOGITS
    ·
    4.64
    ķ
    4.35
    Ģ
    4.34
    ¿
    4.34
    ĺ
    4.30
    ĥ½
    4.27
    ¹
    4.27
    Ŀ
    4.19
    Ĵ
    4.19
    ¤
    4.18
    Activations Density 0.060%

    No Known Activations