© 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 EvalsExportsAPI 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. 26273
    Prev
    Next
    INDEX
    Explanations

    active programming function-related terms or conditions

    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
    17
    +0.23
    1.3%
    47
    +0.15
    0.8%
    347
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.23
    0.05
    157
    +0.15
    0.16
    47
    +0.12
    0.14
    Negative Logits
    FIL
    -1.84
    \[[@
    -1.80
    OUS
    -1.66
    ***
    -1.61
    UH
    -1.60
     COUNTY
    -1.60
    ``
    -1.57
    ULL
    -1.57
    $^{
    -1.57
    umping
    -1.56
    POSITIVE LOGITS
    Ļª
    3.05
    2.99
    ↵  Âł
    2.99
    <|outofrange|>
    2.99
    ↵↵
    2.99
    2.99
    ↵
    2.99
    <|outofrange|>
    2.99
     ↵
    2.99
    ↵
    2.99
    Activations Density 4.020%

    No Known Activations