© 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. 25387
    Prev
    Next
    INDEX
    Explanations

    software development kit (SDK) references and related terms

    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
    98
    +0.15
    0.9%
    156
    +0.14
    0.8%
    422
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.15
    -0.02
    422
    +0.14
    0.05
    203
    +0.13
    0.06
    Negative Logits
    instein
    -1.55
    urred
    -1.50
    ushed
    -1.50
    panic
    -1.46
     \|
    -1.44
     Redistributions
    -1.39
    xymatrix
    -1.39
    ubot
    -1.38
    codec
    -1.38
    ucker
    -1.38
    POSITIVE LOGITS
    liga
    1.74
    folio
    1.61
     possessions
    1.59
    ination
    1.58
    rition
    1.53
     favors
    1.52
    insula
    1.51
     into
    1.43
    cias
    1.43
     jurisdiction
    1.42
    Activations Density 1.623%

    No Known Activations