© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 6493
    Prev
    Next
    INDEX
    Explanations

    mentions of sports fans or fan activities

    oai_token-act-pair · gpt-3.5-turbo

    references to fans in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nom
    -0.67
     Macro
    -0.67
    lished
    -0.67
     MacArthur
    -0.66
    ateral
    -0.63
    framework
    -0.62
    ered
    -0.61
     Johnston
    -0.59
    NC
    -0.58
     Surgery
    -0.58
    POSITIVE LOGITS
    atics
    1.02
     boo
    0.97
    boys
    0.96
    atical
    0.94
     cheering
    0.93
    ubs
    0.92
    verson
    0.90
    haw
    0.87
     chanting
    0.86
     chanted
    0.83
    Activations Density 0.038%

    No Known Activations