© 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. 5383
    Prev
    Next
    INDEX
    Explanations

    instances of physical wrapping or enclosing actions

    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
    312
    +0.13
    0.6%
    598
    +0.13
    0.6%
    369
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.13
    0.06
    526
    +0.13
    -0.01
    577
    +0.11
    0.04
    Negative Logits
    SPONSORED
    -0.76
    DERR
    -0.72
    ADVERTISEMENT
    -0.70
     Ranking
    -0.68
     Corruption
    -0.66
    iation
    -0.64
     awoken
    -0.63
    OPA
    -0.62
     specialization
    -0.61
    eton
    -0.61
    POSITIVE LOGITS
     tightly
    1.05
     sleeves
    0.93
     tighter
    0.89
     securely
    0.84
     snug
    0.81
     scarf
    0.78
     towels
    0.78
     fists
    0.77
     blankets
    0.77
     towel
    0.76
    Activations Density 0.624%

    No Known Activations