© 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. 32386
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to programming concepts and elements of code

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    157
    +0.23
    1.4%
    121
    +0.18
    1.1%
    323
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.23
    0.22
    121
    +0.18
    0.11
    210
    +0.16
    0.04
    Negative Logits
    amous
    -1.65
     whom
    -1.63
    éric
    -1.60
    ionic
    -1.44
    blogger
    -1.43
    vid
    -1.41
    ioned
    -1.40
    onso
    -1.35
    ical
    -1.34
    ifi
    -1.31
    POSITIVE LOGITS
    ¿½
    2.17
    ľ
    2.09
    ĻĤ
    1.97
    Īĺ
    1.94
    ĺ
    1.80
    Ĥ¬
    1.77
    ľĵ
    1.76
    Ķ
    1.76
    ickets
    1.68
    ²
    1.66
    Activations Density 4.307%

    No Known Activations