© 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. 9-RES-JB
    11. 4282
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and physical activities, particularly focusing on specific positions or movements like "right-handed," "left-handed," and "power-play."

    oai_token-act-pair · gpt-3.5-turbo
    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
     Burr
    -0.75
     ®
    -0.73
     Cree
    -0.69
     SX
    -0.67
     Paradox
    -0.66
     Sustainable
    -0.64
     Invisible
    -0.64
     Moj
    -0.64
     CBD
    -0.63
     sq
    -0.63
    POSITIVE LOGITS
    division
    1.15
    season
    1.14
    team
    1.11
    scoring
    1.06
    league
    1.01
    Coach
    1.00
    tackle
    1.00
    goal
    0.97
    player
    0.97
    game
    0.96
    Activations Density 0.123%

    No Known Activations