© 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. 26559
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure in programming languages

    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
    186
    +0.27
    1.6%
    92
    +0.15
    0.9%
    330
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.27
    0.10
    453
    +0.15
    0.09
    330
    +0.12
    0.09
    Negative Logits
    Ļª
    -2.16
    ¥
    -2.05
    ij
    -1.95
    ĵ
    -1.78
    Ī
    -1.77
    Ĺ
    -1.76
    ¢
    -1.70
    Ĭ
    -1.69
    »¿
    -1.68
    Ń
    -1.66
    POSITIVE LOGITS
    blogspot
    1.39
    uginosa
    1.39
     Depression
    1.36
    NER
    1.35
    ness
    1.34
    bral
    1.32
     Photograph
    1.31
    keit
    1.28
     depression
    1.26
    WIND
    1.25
    Activations Density 3.937%

    No Known Activations