© 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. 0-RES-JB
    11. 2822
    Prev
    Next
    INDEX
    Explanations

    phrases related to medication or drugs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pharmaceuticals and medication

    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
    Community
    -0.82
     Cosponsors
    -0.77
    ultural
    -0.70
    TOR
    -0.70
    ero
    -0.69
    ATURE
    -0.68
     heritage
    -0.68
    iler
    -0.67
     Franchise
    -0.65
    akh
    -0.65
    POSITIVE LOGITS
     pills
    3.72
     pill
    2.67
    pill
    2.06
     Pill
    1.77
     capsules
    1.61
     potions
    1.43
     prescriptions
    1.43
     medication
    1.40
     tablets
    1.35
     drugs
    1.35
    Activations Density 0.027%

    No Known Activations