© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28677
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Time" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.10
    0.5%
    420
    +0.10
    0.5%
    186
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.01
    76
    +0.10
    0.03
    288
    +0.10
    0.04
    Negative Logits
     whatsoever
    -0.65
     istg
    -0.63
     pa
    -0.63
     occurring
    -0.62
     coordinate
    -0.60
     incent
    -0.59
     finite
    -0.59
     lag
    -0.58
     bulk
    -0.58
     replay
    -0.58
    POSITIVE LOGITS
     Magazine
    0.92
     Warner
    0.90
     magazine
    0.85
    xit
    0.82
     Inc
    0.80
    hill
    0.79
    iken
    0.77
    Out
    0.76
     Matters
    0.76
    lys
    0.76
    Activations Density 0.373%

    No Known Activations