© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 3921
    Prev
    Next
    INDEX
    Explanations

    references to hands or actions involving hands

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "hand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vell
    -0.86
    nces
    -0.73
     Tonight
    -0.63
     Neigh
    -0.62
    aturday
    -0.62
     Sound
    -0.61
    ETF
    -0.61
     Conclusion
    -0.58
    itals
    -0.57
     Atmosp
    -0.57
    POSITIVE LOGITS
    maid
    1.10
    hand
    0.95
    picked
    0.94
     hand
    0.92
    shake
    0.83
    bag
    0.81
     axe
    0.80
    ily
    0.77
    axe
    0.77
     Hand
    0.76
    Activations Density 0.022%

    No Known Activations