© 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. 9350
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical injuries or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and medical conditions

    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
    -0.91
     committees
    -0.82
    markets
    -0.78
     PACs
    -0.78
    books
    -0.78
     surveys
    -0.76
    sites
    -0.75
     warehouses
    -0.74
    ittees
    -0.73
    classes
    -0.72
    POSITIVE LOGITS
     fracture
    1.36
     concussion
    1.30
     migraine
    1.19
     tumor
    1.17
     diagnosis
    1.17
     ail
    1.17
     relapse
    1.17
     seizure
    1.16
     headache
    1.16
     pulmonary
    1.14
    Activations Density 0.190%

    No Known Activations