© 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. 24176
    Prev
    Next
    INDEX
    Explanations

    references to licensing information or instructions

    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
    +0.17
    1.0%
    23
    +0.16
    0.9%
    25
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.17
    0.03
    25
    +0.16
    0.03
    116
    +0.12
    0.03
    Negative Logits
    enders
    -1.71
    eca
    -1.70
    eners
    -1.69
    apine
    -1.64
    uits
    -1.63
    uit
    -1.61
    urities
    -1.57
    doms
    -1.53
    aurus
    -1.52
    ime
    -1.51
    POSITIVE LOGITS
     cref
    1.72
     Redistributions
    1.61
    Assembly
    1.50
     also
    1.47
     reasoned
    1.46
     Otherwise
    1.42
     detailed
    1.40
    ably
    1.36
    also
    1.36
    cknowled
    1.35
    Activations Density 0.085%

    No Known Activations