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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18780
    Prev
    Next
    INDEX
    Explanations

    plays and strategies in American football

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to football strategies and play formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     achievements
    -0.76
     Nobel
    -0.76
     UNESCO
    -0.75
     Achievement
    -0.74
     honoured
    -0.74
     honour
    -0.73
     Paste
    -0.72
     Achievements
    -0.72
     Oslo
    -0.71
     Kyoto
    -0.70
    POSITIVE LOGITS
     linebackers
    1.27
     blockers
    1.26
     backfield
    1.23
     blocker
    1.17
     linebacker
    1.13
     receivers
    1.10
     zone
    1.09
     linemen
    1.08
     cornerback
    1.07
     fullback
    1.07
    Activations Density 0.265%

    No Known Activations