© 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. 4-RES-JB
    11. 20096
    Prev
    Next
    INDEX
    Explanations

    descriptions of penalties or offenses in sports games

    oai_token-act-pair · gpt-3.5-turbo

    references to penalty kicks and related soccer actions

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

    No Comments

    Negative Logits
    enegger
    -0.93
    netflix
    -0.78
    DragonMagazine
    -0.75
     MFT
    -0.74
    tan
    -0.74
     certs
    -0.71
     Patriarch
    -0.71
     membership
    -0.71
    opia
    -0.70
    Appearance
    -0.68
    POSITIVE LOGITS
     stopp
    1.03
     scorer
    0.99
     clutch
    0.95
     interceptions
    0.95
     foul
    0.95
     touchdown
    0.90
     bounce
    0.87
     teammate
    0.87
     scored
    0.87
     scoring
    0.86
    Activations Density 0.654%

    No Known Activations