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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 22040
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to "Goodell" and "Favre" in this context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of key figures associated with the NFL

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semb
    -0.83
    fold
    -0.83
    TOR
    -0.74
    ker
    -0.71
    mere
    -0.70
     Osw
    -0.70
    Coun
    -0.68
    urdue
    -0.67
    nian
    -0.67
    ISO
    -0.66
    POSITIVE LOGITS
     Goodell
    0.85
     Pwr
    0.79
    orm
    0.71
    ï¸ı
    0.69
    vernment
    0.68
    ente
    0.66
     Limits
    0.65
    reau
    0.64
    ored
    0.64
    orship
    0.64
    Activations Density 0.028%

    No Known Activations