© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 3461
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical gestures involving hands

    oai_token-act-pair · gpt-3.5-turbo

    references to hands and their position or action in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipel
    -0.70
    onday
    -0.68
    atis
    -0.67
     batches
    -0.67
     Ruins
    -0.63
    issions
    -0.60
    oday
    -0.59
    Fresh
    -0.59
     duplication
    -0.58
    oan
    -0.58
    POSITIVE LOGITS
    stretched
    1.00
     shoulders
    0.94
     shoulder
    0.93
     waist
    0.91
     clasp
    0.86
     clenched
    0.85
     fists
    0.83
     hips
    0.81
     salute
    0.80
    raised
    0.75
    Activations Density 0.258%

    No Known Activations