© 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. 11-RES-JB
    11. 6169
    Prev
    Next
    INDEX
    Explanations

    terms related to sports teams and their personnel, including coaches, managers, and players

    oai_token-act-pair · gpt-3.5-turbo

    references to sports management and personnel

    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
     Gutenberg
    -0.84
    imester
    -0.79
    utterstock
    -0.74
    eches
    -0.72
    ertodd
    -0.72
    Examples
    -0.70
    posted
    -0.66
    emn
    -0.66
    reply
    -0.65
    apo
    -0.65
    POSITIVE LOGITS
     coach
    1.66
     coaches
    1.58
     coaching
    1.46
     scout
    1.43
     assistant
    1.37
     scouts
    1.35
     manager
    1.35
     scouting
    1.28
     trainer
    1.25
     GM
    1.25
    Activations Density 0.244%

    No Known Activations