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. 8-RES-JB
    6. 7498
    Prev
    Next
    INDEX
    Explanations

    references to facial hair, particularly beards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to beards and facial hair

    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
    EMS
    -0.86
     GOODMAN
    -0.73
    VD
    -0.73
    phis
    -0.70
    Reviewed
    -0.69
    itored
    -0.67
     Provided
    -0.66
     HHS
    -0.66
    esson
    -0.64
     Administ
    -0.63
    POSITIVE LOGITS
     beard
    1.12
    beard
    1.04
     mustache
    1.04
     shaving
    0.88
     shaved
    0.88
     shave
    0.86
     trimmed
    0.86
     bald
    0.83
     dwarf
    0.80
     grooming
    0.77
    Activations Density 0.052%

    No Known Activations