© 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. 28586
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and corporate entities

    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
    156
    +0.28
    1.7%
    365
    +0.14
    0.8%
    434
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.28
    0.04
    295
    +0.14
    0.03
    87
    +0.12
    0.04
    Negative Logits
    IJ
    -2.23
    ĥ½
    -2.11
    ĺ
    -2.07
    Ĵ
    -1.98
    ↵
    -1.90
    č↵
    -1.90
    -1.90
    ↵
    -1.90
    ↵
    -1.90
    ↵        ↵
    -1.90
    POSITIVE LOGITS
    liness
    1.94
    houses
    1.78
    worth
    1.74
    owners
    1.70
    eren
    1.69
    house
    1.67
    notes
    1.64
    building
    1.63
     spokesman
    1.61
    ees
    1.61
    Activations Density 0.153%

    No Known Activations