© 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. 4-RES-SM
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    technical terms and function calls related to file operations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.12
    0.7%
    315
    +0.11
    0.6%
    383
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.12
    0.05
    35
    +0.11
    -0.00
    85
    +0.11
    0.03
    Negative Logits
    nikov
    -1.86
     Gren
    -1.77
    odal
    -1.61
     Hassan
    -1.61
    ovember
    -1.60
     ($(
    -1.54
    ogo
    -1.51
    naments
    -1.50
     Rocky
    -1.48
     decorations
    -1.46
    POSITIVE LOGITS
     read
    4.00
     reading
    3.69
     Reader
    3.44
     reader
    3.30
    reader
    3.27
     Read
    3.13
    read
    3.08
     Reading
    3.02
     reads
    2.99
     readers
    2.92
    Activations Density 1.010%

    No Known Activations