© 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. 2-RES-SM
    11. 14111
    Prev
    Next
    INDEX
    Explanations

    elements related to coding syntax and structure

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    172
    +0.15
    0.8%
    345
    +0.12
    0.7%
    196
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.15
    0.06
    200
    +0.12
    0.04
    177
    +0.10
    0.03
    Negative Logits
    jour
    -1.79
     occasion
    -1.64
     occasions
    -1.60
    ftware
    -1.55
    ipeg
    -1.49
    rives
    -1.46
     whatsoever
    -1.43
     GMT
    -1.41
    comes
    -1.40
    ancouver
    -1.40
    POSITIVE LOGITS
    al
    1.83
    esis
    1.67
    ÃŃvel
    1.63
    orio
    1.61
    ashi
    1.61
    garten
    1.51
    alc
    1.48
    ÃŃs
    1.47
    acion
    1.43
    us
    1.43
    Activations Density 0.794%

    No Known Activations