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

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 5827
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and interactions between individuals

    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
    665
    +0.10
    0.5%
    290
    +0.09
    0.4%
    242
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.05
    324
    +0.09
    0.04
    105
    +0.09
    0.04
    Negative Logits
    ãĥĩãĤ£
    -0.68
     eyebrow
    -0.65
     bone
    -0.64
     sounding
    -0.63
     crust
    -0.59
     overlap
    -0.56
    ipes
    -0.56
     glim
    -0.56
     actionGroup
    -0.55
     inhib
    -0.55
    POSITIVE LOGITS
     onwards
    0.84
     onward
    0.82
     downstairs
    0.75
    verning
    0.75
     upstairs
    0.74
    Ô
    0.74
     toward
    0.72
     Steps
    0.72
     ashore
    0.69
     towards
    0.68
    Activations Density 0.263%

    No Known Activations