© 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. 9-RES-JB
    11. 15381
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or organizations, particularly Borussia Dortmund

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Borussia, possibly 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.99
    mine
    -0.95
    voy
    -0.92
    liam
    -0.89
    lio
    -0.87
    rint
    -0.87
    andro
    -0.86
    worms
    -0.86
    ascript
    -0.86
    allo
    -0.86
    POSITIVE LOGITS
    ש
    0.80
     Volks
    0.78
     ASCII
    0.78
     Sar
    0.77
     Alpha
    0.75
    ×Ķ
    0.75
     Dortmund
    0.73
     Organisation
    0.71
     Ban
    0.71
     {}
    0.70
    Activations Density 0.233%

    No Known Activations