© 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. 3-RES-JB
    11. 21692
    Prev
    Next
    INDEX
    Explanations

    names and terms related to football (soccer)

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific individuals and teams in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Anonymous
    -1.02
     PBS
    -0.94
     Navajo
    -0.92
     Cherokee
    -0.90
    MIT
    -0.89
    Zip
    -0.88
    achusetts
    -0.87
     nonprofits
    -0.87
    FBI
    -0.87
    enegger
    -0.85
    POSITIVE LOGITS
     goalkeeper
    1.27
     footballer
    1.17
     defences
    1.17
     striker
    1.16
     winger
    1.14
     midfielder
    1.13
     relegation
    1.09
     Guardiola
    1.08
     Football
    1.08
     centre
    1.05
    Activations Density 0.447%

    No Known Activations