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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 4447
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, specifically ACL tears

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ligaments and ACL injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wealth
    -0.79
     Michaels
    -0.79
     Dash
    -0.77
    Dash
    -0.76
    Hour
    -0.72
    chart
    -0.70
     Startup
    -0.70
     Idle
    -0.69
     Sunshine
    -0.69
    utt
    -0.68
    POSITIVE LOGITS
     lig
    3.97
     ACL
    1.85
     agon
    1.57
     tendon
    1.49
     verte
    1.32
     Liga
    1.26
    lig
    1.25
     arthritis
    1.14
     receptor
    1.13
     fem
    1.12
    Activations Density 0.042%

    No Known Activations