© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24385
    Prev
    Next
    INDEX
    Explanations

    medical injuries and conditions related to physical trauma, particularly focusing on torn ligaments such as ACL tears

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries, particularly related to sports or physical activities

    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
    nces
    -0.94
    soDeliveryDate
    -0.76
    taboola
    -0.75
    groups
    -0.75
    appings
    -0.74
    vernment
    -0.72
    holders
    -0.71
    ername
    -0.69
    stakes
    -0.67
    boats
    -0.67
    POSITIVE LOGITS
     hamstring
    1.44
     tendon
    1.42
     Achilles
    1.35
     knee
    1.35
     ACL
    1.35
     ankle
    1.34
     groin
    1.29
     elbow
    1.29
     lig
    1.27
     ribs
    1.25
    Activations Density 0.101%

    No Known Activations