© 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. 8-RES-JB
    11. 770
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletic performance statistics

    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
    •single token firings
    fires on " unbeaten", "QB", " winger", other sports terms

    No Comments

    Negative Logits
    enegger
    -0.98
    schild
    -0.65
    sylv
    -0.65
    Prin
    -0.65
    Els
    -0.61
     umb
    -0.58
     PBS
    -0.58
    abus
    -0.56
     Quartz
    -0.56
     unsupported
    -0.56
    POSITIVE LOGITS
     scoring
    1.05
     goalkeeper
    1.05
     midfield
    1.01
     scorer
    1.01
     winger
    0.99
     defender
    0.99
     playoff
    0.98
     outfield
    0.98
     infield
    0.97
     midfielder
    0.96
    Activations Density 1.343%

    No Known Activations