© 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. 13090
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their activities

    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
    451
    +0.17
    1.0%
    156
    +0.14
    0.8%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.17
    0.03
    477
    +0.14
    0.04
    26
    +0.12
    0.02
    Negative Logits
    Ģ
    -2.98
    Ĵ
    -2.95
    Ħ
    -2.77
    ±
    -2.77
    ¬
    -2.76
    ĥ½
    -2.74
    į
    -2.71
    ĨĴ
    -2.70
    ¯
    -2.69
    ĩ
    -2.68
    POSITIVE LOGITS
    yard
    2.47
    yards
    2.08
    children
    2.00
    girl
    2.00
    boys
    1.93
    work
    1.93
    house
    1.89
    boy
    1.88
     attendance
    1.83
     sophomore
    1.82
    Activations Density 0.182%

    No Known Activations