© 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. 2-RES-SM
    11. 13830
    Prev
    Next
    INDEX
    Explanations

    references to data structures and variable assignments in programming contexts

    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
    342
    +0.15
    0.8%
    233
    +0.14
    0.8%
    186
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.02
    21
    +0.14
    0.07
    136
    +0.13
    -0.04
    Negative Logits
    Īĺ
    -1.69
    ĺ
    -1.65
    Ī
    -1.64
    ETHOD
    -1.54
    uments
    -1.53
    ĸ
    -1.52
    ļ
    -1.52
    reements
    -1.50
    ¤
    -1.48
    suits
    -1.43
    POSITIVE LOGITS
    "];
    1.50
    "]
    1.40
     heels
    1.39
     interchange
    1.38
    .""
    1.36
    dere
    1.35
    unnumbered
    1.34
     THEN
    1.34
    '].
    1.34
    ']
    1.32
    Activations Density 2.929%

    No Known Activations