© 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 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. 9-RES-JB
    11. 18210
    Prev
    Next
    INDEX
    Explanations

    references to playing or handling a ball in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    references to the ball and puck in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.72
     Borders
    -0.72
    Scient
    -0.70
     Beef
    -0.70
     Canaver
    -0.70
     Cind
    -0.69
     Buddh
    -0.69
     Restaur
    -0.68
     Profit
    -0.68
     Norn
    -0.66
    POSITIVE LOGITS
    handler
    1.18
     carrier
    0.98
     handler
    0.87
    players
    0.86
    player
    0.86
    hand
    0.85
    ball
    0.82
    pit
    0.81
    wright
    0.78
    atu
    0.78
    Activations Density 0.028%

    No Known Activations