© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10198
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical actions involving grabbing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grab."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hedge
    -0.63
     dilig
    -0.61
     denomin
    -0.59
     alias
    -0.59
     reconc
    -0.57
    REDACTED
    -0.57
     Contrast
    -0.56
     ende
    -0.56
     subtitle
    -0.55
    bard
    -0.54
    POSITIVE LOGITS
     grab
    1.01
     grabbing
    0.91
    bers
    0.82
    ãĥ¼ãĥ³
    0.82
    rolet
    0.80
    ById
    0.80
    grab
    0.78
    iques
    0.77
    rill
    0.77
    amaz
    0.77
    Activations Density 0.007%

    No Known Activations