© 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. 1-RES-SM
    11. 29174
    Prev
    Next
    INDEX
    Explanations

    URLs in the text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.14
    0.8%
    0
    +0.14
    0.8%
    73
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.14
    0.04
    500
    +0.14
    0.04
    0
    +0.13
    0.04
    Negative Logits
    "}](#
    -1.70
    )">
    -1.59
    )](#
    -1.53
     Instruments
    -1.50
     *
    -1.48
    "/>
    -1.44
    ators
    -1.44
     enable
    -1.42
    ,^[@
    -1.39
    ](
    -1.39
    POSITIVE LOGITS
    IJ
    2.00
    ľĵ
    1.93
    ĥ½
    1.81
    Ĵ
    1.60
    Į
    1.59
    Ĩ
    1.56
    Ľ
    1.56
     ur
    1.54
     breath
    1.53
    ĥ
    1.53
    Activations Density 0.060%

    No Known Activations