© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    phrases related to health conditions and medical attributes

    oai_token-act-pair · gpt-3.5-turbo
    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
    wark
    -0.77
    rail
    -0.70
    rand
    -0.70
    hack
    -0.68
    oult
    -0.67
    cade
    -0.67
    doing
    -0.66
    ernaut
    -0.65
    March
    -0.65
    alion
    -0.63
    POSITIVE LOGITS
     disabilities
    1.71
     histories
    1.09
     differing
    1.02
     weakened
    1.02
     severe
    1.00
     autism
    0.99
     incomes
    0.97
     impair
    0.96
     compromised
    0.94
     impaired
    0.93
    Activations Density 0.107%

    No Known Activations