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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 21343
    Prev
    Next
    INDEX
    Explanations

    verbs related to sports actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of competitive sports actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     WATCHED
    -0.69
    ploma
    -0.63
     endorsement
    -0.63
     attends
    -0.63
     Profession
    -0.62
     acquaintance
    -0.62
    OPLE
    -0.61
     unemploy
    -0.61
    lihood
    -0.59
     endors
    -0.59
    POSITIVE LOGITS
     halftime
    0.97
     offensively
    0.88
     defensively
    0.83
     unanswered
    0.79
     turnovers
    0.79
     territ
    0.71
     rallied
    0.71
     onslaught
    0.70
     shorth
    0.69
     retake
    0.69
    Activations Density 0.241%

    No Known Activations