© 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. 18659
    Prev
    Next
    INDEX
    Explanations

    terms related to high skill or performance levels in sports or physical activities

    oai_token-act-pair · gpt-3.5-turbo

    references to elite and high-performing athletes

    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
    soDeliveryDate
    -0.93
    abeth
    -0.76
    skirts
    -0.72
     Cosponsors
    -0.71
    paces
    -0.70
    ventures
    -0.70
    votes
    -0.68
     holidays
    -0.67
     Canaver
    -0.67
    netflix
    -0.66
    POSITIVE LOGITS
     passer
    1.47
     player
    1.44
     athlete
    1.43
     scorer
    1.36
     defender
    1.35
     hitter
    1.35
     performer
    1.27
     prospect
    1.23
     footballer
    1.21
     blocker
    1.20
    Activations Density 0.149%

    No Known Activations