© 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. 4-RES-SM
    11. 9096
    Prev
    Next
    INDEX
    Explanations

    error messages and exceptions in a programming context

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    390
    +0.15
    0.9%
    21
    +0.12
    0.7%
    38
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.00
    181
    +0.12
    0.04
    148
    +0.11
    0.03
    Negative Logits
    zzles
    -1.72
    eman
    -1.70
     hassle
    -1.65
    manship
    -1.62
    ership
    -1.56
    esta
    -1.48
    ils
    -1.47
    kered
    -1.41
    creen
    -1.39
    overnment
    -1.38
    POSITIVE LOGITS
    ¡
    2.79
    Ł
    2.64
    ¦
    2.57
    ¨
    2.48
    ł
    2.44
    Į
    2.41
    ľĵ
    2.33
    ©
    2.33
    Ķ
    2.33
    ·
    2.32
    Activations Density 0.194%

    No Known Activations