© 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. 8-RES-JB
    11. 20366
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sports and teamwork

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to teamwork and player development in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uphem
    -0.93
     inconvenient
    -0.90
    vier
    -0.86
    irens
    -0.72
    addafi
    -0.69
    utterstock
    -0.69
    9999
    -0.69
     spotted
    -0.69
    claimed
    -0.68
     briefly
    -0.67
    POSITIVE LOGITS
     coaching
    1.26
     teammates
    0.98
     TEAM
    0.96
     athletics
    0.95
     coaches
    0.95
     clubhouse
    0.94
     fanbase
    0.93
     team
    0.88
     athlet
    0.87
     youth
    0.86
    Activations Density 0.644%

    No Known Activations