Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5758
    Prev
    Next
    INDEX
    Explanations

    references to physical actions involving fists

    oai_token-act-pair · gpt-3.5-turbo

    references to 'fist'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trends
    -0.73
    ables
    -0.68
    ors
    -0.66
     Architects
    -0.65
     Trend
    -0.65
     Lowry
    -0.64
    information
    -0.64
     Intelligent
    -0.64
     deter
    -0.64
     Hilbert
    -0.63
    POSITIVE LOGITS
     fist
    3.73
     fists
    3.18
     Fist
    2.01
     clenched
    1.69
     paw
    1.40
     handshake
    1.36
     forearm
    1.35
     claws
    1.33
     palm
    1.30
     claw
    1.29
    Activations Density 0.026%

    No Known Activations