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. 11-RES-JB
    6. 4465
    Prev
    Next
    INDEX
    Explanations

    individual actions related to physical gestures, such as shaking heads and raising hands

    oai_token-act-pair · gpt-3.5-turbo

    references to physical gestures and movements of the head and arms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.60
    whose
    -0.60
    cial
    -0.59
    Ranked
    -0.59
     Provided
    -0.58
    folios
    -0.57
    cially
    -0.57
    prototype
    -0.56
    ndra
    -0.55
     Plane
    -0.54
    POSITIVE LOGITS
     vigorously
    1.07
     disappro
    0.99
     knowingly
    0.96
     symp
    0.94
     politely
    0.93
     goodbye
    0.89
     respectfully
    0.87
     enthusiastically
    0.85
     approving
    0.85
     emphatically
    0.82
    Activations Density 0.082%

    No Known Activations