© 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. 31284
    Prev
    Next
    INDEX
    Explanations

    instances of research findings or observations in scientific 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
    326
    +0.12
    0.7%
    392
    +0.11
    0.6%
    234
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.12
    0.04
    21
    +0.11
    0.03
    65
    +0.11
    0.03
    Negative Logits
    »¿
    -3.86
    Ľ
    -3.83
    -3.67
    -3.67
    ↵↵
    -3.67
    ↵
    -3.67
     ↵
    -3.67
    ↵↵
    -3.67
    <|outofrange|>
    -3.67
    ↵
    -3.67
    POSITIVE LOGITS
    tol
    1.61
     homology
    1.57
    Lemma
    1.56
    Nil
    1.55
     ^[@
    1.51
    given
    1.50
    .^[@
    1.48
     allele
    1.45
    oding
    1.44
    quet
    1.42
    Activations Density 0.161%

    No Known Activations