© 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. 27793
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorship or creation of content

    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
    497
    +0.14
    0.8%
    288
    +0.13
    0.7%
    486
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.14
    0.03
    288
    +0.13
    0.04
    69
    +0.12
    0.04
    Negative Logits
    vent
    -1.82
    ).[
    -1.60
     involved
    -1.59
    ."[
    -1.52
    \[[@
    -1.50
    fall
    -1.49
    âĢIJ
    -1.49
     regulated
    -1.42
    odend
    -1.42
    inally
    -1.40
    POSITIVE LOGITS
    ľĵ
    2.00
    ±
    1.69
    href
    1.61
    ©
    1.61
    ĸ´
    1.52
     Description
    1.51
     comments
    1.51
     Comments
    1.49
     topic
    1.48
     @
    1.47
    Activations Density 0.278%

    No Known Activations