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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 3605
    Prev
    Next
    INDEX
    Explanations

    injuries related to muscles and joints

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with sports injuries, particularly focusing on hamstring and ankle injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.81
    rising
    -0.74
    eworld
    -0.71
    lists
    -0.71
    ramer
    -0.70
     Cosponsors
    -0.69
    avanaugh
    -0.69
    zanne
    -0.68
    units
    -0.68
    compan
    -0.67
    POSITIVE LOGITS
     tendon
    1.46
     lig
    1.22
     injury
    1.20
     injuries
    0.97
     Injury
    0.96
     suffered
    0.95
     muscle
    0.93
     sustained
    0.92
     inflammation
    0.92
     surgery
    0.90
    Activations Density 0.068%

    No Known Activations