© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24303
    Prev
    Next
    INDEX
    Explanations

    descriptions related to American football plays

    oai_token-act-pair · gpt-3.5-turbo

    actions and strategies in football plays

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     organis
    -0.93
     ageing
    -0.89
     organisations
    -0.87
     achievements
    -0.86
     Rowling
    -0.81
     organisers
    -0.81
     organising
    -0.78
     honoured
    -0.78
     Governments
    -0.77
     fulfil
    -0.76
    POSITIVE LOGITS
     blocker
    1.09
     scrimmage
    1.07
    tackle
    0.99
     ball
    0.97
     timeout
    0.96
     fastball
    0.95
     linebackers
    0.95
     Kaepernick
    0.93
     punt
    0.92
     blockers
    0.91
    Activations Density 0.338%

    No Known Activations