© 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. 8-RES-JB
    11. 3089
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions, particularly focusing on the verb "punch"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "punch" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uve
    -0.85
    abeth
    -0.75
    icter
    -0.71
    abor
    -0.70
    aird
    -0.69
    izen
    -0.64
    uph
    -0.63
    bec
    -0.62
    ignty
    -0.61
    heimer
    -0.61
    POSITIVE LOGITS
    bowl
    1.26
     holes
    0.81
     punch
    0.80
    bag
    0.77
     punches
    0.77
    bags
    0.77
    weed
    0.76
    apult
    0.75
    card
    0.73
    ting
    0.73
    Activations Density 0.043%

    No Known Activations