© 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. 30612
    Prev
    Next
    INDEX
    Explanations

    closing comment syntax in source code

    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
    422
    +0.12
    0.6%
    350
    +0.12
    0.6%
    424
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.12
    0.02
    422
    +0.12
    0.03
    350
    +0.11
    0.03
    Negative Logits
    ...](
    -1.97
    stim
    -1.87
     ones
    -1.82
    )](
    -1.78
    )."
    -1.68
    )].
    -1.62
    oretic
    -1.60
    worthy
    -1.59
    ?).
    -1.55
    blast
    -1.54
    POSITIVE LOGITS
    ¦
    2.67
    ģ
    2.21
    ¶
    2.06
    ħ
    2.02
    Ĥ¬
    2.02
    °
    1.98
    ³
    1.98
    İ
    1.92
    ī
    1.91
    ij
    1.89
    Activations Density 0.072%

    No Known Activations