© 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. 10227
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations involving divisors and factors

    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
    78
    +0.21
    1.3%
    392
    +0.12
    0.7%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.21
    0.00
    448
    +0.12
    0.02
    255
    +0.11
    -0.00
    Negative Logits
     “
    -1.55
     “[
    -1.42
    )—
    -1.32
    utenant
    -1.31
    rès
    -1.25
    ));
    -1.25
    opically
    -1.22
    )–
    -1.22
    ,”
    -1.22
    mente
    -1.20
    POSITIVE LOGITS
    ¥
    1.86
    ī
    1.81
    Ĩ
    1.74
    ©
    1.70
    »
    1.67
    ¤
    1.65
    £
    1.64
    **_
    1.61
    ĵ
    1.54
    §
    1.52
    Activations Density 0.047%

    No Known Activations