© 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. 1-RES-SM
    11. 24435
    Prev
    Next
    INDEX
    Explanations

    code snippets or expressions related to function definitions and calls

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.18
    1.0%
    100
    +0.13
    0.7%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.18
    0.04
    451
    +0.13
    0.03
    219
    +0.13
    0.04
    Negative Logits
    \]](
    -1.95
    iemann
    -1.85
    ocene
    -1.85
    orian
    -1.74
    ]{.
    -1.72
    ](
    -1.68
    )\]
    -1.67
    \].
    -1.65
    .](
    -1.64
    )\].
    -1.63
    POSITIVE LOGITS
    Ĥ
    2.58
    Į
    2.50
    İ
    2.46
    Ĥ¬
    2.45
    ľĵ
    2.32
    ¹
    2.31
    Ķ
    2.29
    ¿½
    2.28
    IJ
    2.27
    °
    2.25
    Activations Density 0.120%

    No Known Activations