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. 1-RES-JB
    6. 23934
    Prev
    Next
    INDEX
    Explanations

    mentions of materials or items related to construction or woodworking, particularly wood

    oai_token-act-pair · gpt-3.5-turbo

    references to wood as a material

    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
    uberty
    -0.83
     aver
    -0.78
    enance
    -0.66
     Epstein
    -0.66
     Shapiro
    -0.65
     Boyle
    -0.63
     Katz
    -0.62
     Carey
    -0.61
    VICE
    -0.61
     Friedman
    -0.61
    POSITIVE LOGITS
     wood
    1.12
    wood
    1.04
    lake
    1.01
    \\\\\\\\
    0.92
    lands
    0.91
    working
    0.89
    ruff
    0.88
    worker
    0.88
    riter
    0.88
    wind
    0.85
    Activations Density 0.011%

    No Known Activations