© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    words that are related to physical body parts or actions associated with them

    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
    397
    +0.11
    0.5%
    108
    +0.11
    0.5%
    745
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.02
    232
    +0.11
    0.05
    284
    +0.11
    0.04
    Negative Logits
     Canaver
    -0.67
     Solitaire
    -0.66
    ãĥ¯
    -0.64
    isu
    -0.62
     siph
    -0.62
    peror
    -0.58
     grease
    -0.57
     foc
    -0.56
     slicing
    -0.55
     fer
    -0.55
    POSITIVE LOGITS
    ifully
    0.92
    iful
    0.86
    ieth
    0.86
    yp
    0.85
    hene
    0.79
    rou
    0.79
    ather
    0.77
    osaurs
    0.75
    hett
    0.73
    owitz
    0.72
    Activations Density 0.294%

    No Known Activations