Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8915
    Prev
    Next
    INDEX
    Explanations

    information related to injuries and medical conditions in professional sports, specifically knee injuries and surgeries in a football context

    oai_token-act-pair · gpt-3.5-turbo

    information related to injuries in sports

    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
     hydra
    -0.84
     propagation
    -0.82
     cascade
    -0.80
     propagate
    -0.80
    APS
    -0.78
     Roses
    -0.78
    hesive
    -0.77
     Hydra
    -0.77
     pse
    -0.76
     rake
    -0.74
    POSITIVE LOGITS
    Dun
    2.15
     Dun
    2.14
     Dur
    1.58
    Dur
    1.57
     Duncan
    1.51
     Dunham
    1.49
     dun
    1.35
    Bon
    1.17
     Dunk
    1.12
     Tun
    1.11
    Activations Density 0.331%

    No Known Activations