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. 20579
    Prev
    Next
    INDEX
    Explanations

    names of sports teams from various cities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and cities

    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
    enegger
    -1.15
    schild
    -1.11
    ngth
    -0.79
    aird
    -0.78
    ibliography
    -0.78
    olkien
    -0.77
    netflix
    -0.76
    nces
    -0.76
    adj
    -0.72
    haar
    -0.72
    POSITIVE LOGITS
     Eagles
    1.16
     Giants
    1.11
     Falcons
    1.10
     Jets
    1.10
     Wolves
    1.05
     Cardinals
    1.05
     Buccaneers
    1.04
     Ducks
    1.02
     Royals
    1.02
     Panthers
    1.02
    Activations Density 0.114%

    No Known Activations