© 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. 12652
    Prev
    Next
    INDEX
    Explanations

    elements and terms associated with programming and system structures

    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
    63
    +0.15
    0.9%
    422
    +0.14
    0.8%
    161
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.15
    0.11
    234
    +0.14
    0.15
    142
    +0.13
    0.13
    Negative Logits
    igens
    -2.05
    igen
    -1.72
     rub
    -1.63
    optera
    -1.52
    ection
    -1.52
    mond
    -1.51
    landers
    -1.51
    orems
    -1.39
    umen
    -1.39
    imeter
    -1.38
    POSITIVE LOGITS
     respectively
    1.60
     affiliated
    1.47
    **.
    1.43
     authors
    1.41
     alike
    1.39
    operated
    1.35
     exclusive
    1.35
    >";
    1.33
    ialize
    1.33
    .—
    1.27
    Activations Density 7.190%

    No Known Activations