© 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. 2-RES-JB
    11. 19844
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions or health issues that are problematic and potentially serious

    oai_token-act-pair · gpt-3.5-turbo

    mentions of medical complications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bors
    -0.88
    amaru
    -0.84
    berman
    -0.83
    bor
    -0.77
    kers
    -0.76
    liam
    -0.74
    erness
    -0.72
    este
    -0.72
    ership
    -0.72
    ers
    -0.71
    POSITIVE LOGITS
     complications
    1.22
     complication
    1.16
    èĢħ
    0.78
     complicate
    0.76
     ens
    0.75
     disse
    0.73
     inconven
    0.71
     traged
    0.70
    ilial
    0.69
     headaches
    0.68
    Activations Density 0.010%

    No Known Activations