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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 18963
    Prev
    Next
    INDEX
    Explanations

    keywords related to the **Spider-Man** franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Spider-Man."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grains
    -0.82
     grain
    -0.79
    aired
    -0.78
    heastern
    -0.75
    REAM
    -0.74
    ãĤ·ãĥ£
    -0.69
     Seym
    -0.68
    bred
    -0.67
    iliated
    -0.67
    renched
    -0.66
    POSITIVE LOGITS
     Bros
    0.88
     Apocalypse
    0.82
    chu
    0.79
    âĦ¢
    0.78
     Kenobi
    0.78
     Noir
    0.77
    âĦ¢:
    0.77
     Barbie
    0.76
    hattan
    0.75
    Batman
    0.74
    Activations Density 0.026%

    No Known Activations