© 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. 8709
    Prev
    Next
    INDEX
    Explanations

    terms related to counting or listing

    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
    307
    +0.14
    0.8%
    505
    +0.12
    0.6%
    68
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.14
    0.02
    38
    +0.12
    0.03
    164
    +0.11
    0.04
    Negative Logits
    ¸
    -2.29
    ħ
    -1.99
    Ń
    -1.91
    ½
    -1.86
    ĭ
    -1.85
    ·
    -1.84
    ı
    -1.78
    ¿½
    -1.75
    hetics
    -1.70
    ³
    -1.69
    POSITIVE LOGITS
    press
    2.99
    sworth
    2.64
    smith
    2.49
    play
    2.46
    break
    2.43
    paste
    2.36
    maker
    2.24
    mith
    2.21
    lessness
    2.18
    stress
    2.13
    Activations Density 0.401%

    No Known Activations