© 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 EvalsExportsAPI 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. 10255
    Prev
    Next
    INDEX
    Explanations

    code comments related to errors and debugging

    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
    478
    +0.17
    1.0%
    106
    +0.13
    0.7%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.17
    0.03
    360
    +0.13
    0.02
    106
    +0.11
    0.03
    Negative Logits
    )].
    -2.03
    )](
    -1.89
    ...](
    -1.88
    []{
    -1.84
    ).](
    -1.75
    ceral
    -1.69
    .[]{
    -1.65
    icorn
    -1.62
    arios
    -1.61
    *]{}.
    -1.60
    POSITIVE LOGITS
     mind
    1.71
     void
    1.64
     reckless
    1.60
     coward
    1.55
     wound
    1.52
     unconscious
    1.44
     damn
    1.44
     heed
    1.42
     absence
    1.41
     ÑĩÑĤо
    1.39
    Activations Density 0.074%

    No Known Activations