© 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. 11-RES-JB
    11. 8835
    Prev
    Next
    INDEX
    Explanations

    words related to sports competitions, such as "competition," "win," "victory," "gold," and "medals."

    oai_token-act-pair · gpt-3.5-turbo

    events related to competitive sports and athletic achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.92
     Commun
    -0.71
     Pediatrics
    -0.69
    Det
    -0.69
    agency
    -0.68
     memo
    -0.66
    =#
    -0.64
    artisan
    -0.63
    engineering
    -0.63
     Migration
    -0.63
    POSITIVE LOGITS
     competed
    1.45
     undefeated
    1.31
     defeated
    1.31
     victorious
    1.29
     unbeaten
    1.27
     disqualified
    1.23
     vanquished
    1.20
     rematch
    1.19
     winning
    1.16
     beaten
    1.15
    Activations Density 0.434%

    No Known Activations