© 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. 12-RES-JB
    11. 4527
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and names, particularly in the context of football teams, players, and positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of football players and their positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pse
    -0.86
     confir
    -0.84
     estab
    -0.79
     piercing
    -0.78
     subp
    -0.75
     prevail
    -0.74
     quoting
    -0.70
     ATK
    -0.69
     spec
    -0.68
     Hearts
    -0.68
    POSITIVE LOGITS
    Sean
    1.33
    Marcus
    1.30
    Andre
    1.30
    onte
    1.24
    Angelo
    1.23
    ante
    1.20
    vin
    1.18
    Marco
    1.17
    andre
    1.16
    von
    1.14
    Activations Density 0.112%

    No Known Activations