© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4925
    Prev
    Next
    INDEX
    Explanations

    mentions of competitive events or contests, especially in relation to cycling or races

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    128
    +0.19
    0.9%
    587
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.04
    326
    +0.10
    0.03
    659
    +0.09
    0.02
    Negative Logits
    yang
    -0.71
    forward
    -0.70
    cott
    -0.69
    ments
    -0.69
    mented
    -0.62
    arded
    -0.59
     Sne
    -0.58
    mentation
    -0.58
    washed
    -0.57
    washing
    -0.57
    POSITIVE LOGITS
    ists
    1.71
    ist
    1.54
    ism
    1.26
    istic
    1.25
    istically
    1.11
    istry
    0.99
    ista
    0.98
    iste
    0.94
    ologue
    0.94
    IST
    0.93
    Activations Density 0.167%

    No Known Activations