© 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. 1-RES-SM
    11. 24103
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs

    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
    +0.20
    1.1%
    69
    +0.19
    1.1%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.20
    0.13
    151
    +0.19
    0.06
    434
    +0.13
    0.06
    Negative Logits
    actin
    -1.72
    iere
    -1.68
    imet
    -1.62
    clin
    -1.58
     broch
    -1.57
    enthal
    -1.54
    esque
    -1.54
    pit
    -1.53
    иÑĤелÑĮ
    -1.51
    imeter
    -1.51
    POSITIVE LOGITS
     sanity
    1.86
     #{
    1.79
     violate
    1.77
    asts
    1.77
     hers
    1.72
     duplicate
    1.65
     replace
    1.64
     yours
    1.63
     hash
    1.63
     <%=
    1.59
    Activations Density 0.551%

    No Known Activations