© 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. 12758
    Prev
    Next
    INDEX
    Explanations

    patterns related to error handling and exceptions 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
    186
    +0.17
    1.0%
    507
    +0.15
    0.9%
    320
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.17
    0.04
    207
    +0.15
    0.05
    78
    +0.12
    0.05
    Negative Logits
     season
    -1.42
     minded
    -1.38
    unnumbered
    -1.25
     schools
    -1.21
    ever
    -1.20
     seasons
    -1.19
    door
    -1.19
    throws
    -1.16
    irections
    -1.14
     premie
    -1.14
    POSITIVE LOGITS
     teammate
    1.42
    ા
    1.37
    à«
    1.29
    ices
    1.27
    ESULT
    1.26
    rup
    1.20
    vester
    1.18
    auc
    1.18
     streak
    1.17
     bleeding
    1.17
    Activations Density 4.521%

    No Known Activations