© 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. 25330
    Prev
    Next
    INDEX
    Explanations

    phrases related to capture or capturing events

    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
    410
    +0.14
    0.8%
    148
    +0.14
    0.8%
    177
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.02
    410
    +0.14
    0.02
    148
    +0.13
    0.01
    Negative Logits
    xtures
    -1.69
    xture
    -1.67
    rror
    -1.57
    MODULE
    -1.43
    remia
    -1.39
     hereby
    -1.36
    \!\!
    -1.34
    STEM
    -1.34
     Centers
    -1.32
    \!\!\!\!
    -1.31
    POSITIVE LOGITS
    thouse
    1.79
    ured
    1.79
    ains
    1.78
    uration
    1.73
    urous
    1.71
    son
    1.65
    borough
    1.63
    itudes
    1.60
    itude
    1.59
    shots
    1.57
    Activations Density 0.082%

    No Known Activations