© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    phrases indicating origins or starting points

    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
    122
    +0.13
    0.7%
    278
    +0.12
    0.7%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.13
    0.04
    91
    +0.12
    0.04
    155
    +0.12
    0.03
    Negative Logits
    º
    -2.68
    Ĥ¬
    -2.43
    ¾
    -2.40
    ¿
    -2.35
    ª
    -2.32
    ¥
    -2.32
    ¢
    -2.27
    ²
    -2.23
    ģ
    -2.23
    °
    -2.18
    POSITIVE LOGITS
     whence
    1.94
     abroad
    1.80
     September
    1.79
     January
    1.76
     October
    1.76
     November
    1.75
     inception
    1.75
     February
    1.71
     August
    1.70
     April
    1.69
    Activations Density 0.174%

    No Known Activations