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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 19548
    Prev
    Next
    INDEX
    Explanations

    expressions or actions that symbolize a message or feeling

    oai_token-act-pair · gpt-3.5-turbo

    references to gestures and symbolic actions

    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
    ondo
    -0.82
    teen
    -0.76
    ccording
    -0.74
    fortable
    -0.72
    src
    -0.69
    elsen
    -0.68
    ameron
    -0.68
    aryl
    -0.68
    unker
    -0.66
    sis
    -0.66
    POSITIVE LOGITS
     gesture
    1.75
     gestures
    1.43
     salute
    0.97
     towards
    0.78
     Canaver
    0.73
    eers
    0.72
    itives
    0.71
     recogn
    0.70
     swipe
    0.70
     vibration
    0.70
    Activations Density 0.006%

    No Known Activations