© 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. 24669
    Prev
    Next
    INDEX
    Explanations

    mentions of experimental and extension-related content

    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
    308
    +0.17
    0.9%
    194
    +0.16
    0.9%
    203
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.17
    0.02
    194
    +0.16
    0.03
    203
    +0.15
    0.02
    Negative Logits
    king
    -1.96
    Ļª
    -1.94
    Ĥ¬
    -1.77
    ily
    -1.69
    "){
    -1.64
    athan
    -1.61
     herself
    -1.60
    unnumbered
    -1.60
    ¾
    -1.55
    ously
    -1.53
    POSITIVE LOGITS
    remely
    2.07
    reme
    1.82
    inction
    1.75
    raction
    1.66
    ensible
    1.61
    ricular
    1.54
    ensive
    1.51
    aneous
    1.50
    rex
    1.43
    riber
    1.41
    Activations Density 0.064%

    No Known Activations