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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7585
    Prev
    Next
    INDEX
    Explanations

    sports scores, particularly from soccer matches

    oai_token-act-pair · gpt-3.5-turbo

    numerical scores in sports-related contexts

    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
    wives
    -0.87
    classes
    -0.84
    forms
    -0.83
    photos
    -0.81
    rooms
    -0.77
    pots
    -0.74
    many
    -0.74
    pects
    -0.73
    agents
    -0.73
    ources
    -0.72
    POSITIVE LOGITS
     victory
    1.20
     rout
    1.12
     setback
    1.10
     halftime
    1.09
     loss
    1.08
     deficit
    1.05
     comeback
    1.05
     defeat
    1.03
     win
    0.99
     record
    0.96
    Activations Density 0.042%

    No Known Activations