© 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. 4-RES-JB
    11. 10106
    Prev
    Next
    INDEX
    Explanations

    mentions or variations of the word "prescribed"

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to prescribed medications and their usage

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

    No Comments

    Negative Logits
     Strait
    -0.79
     Gutenberg
    -0.77
    iland
    -0.75
     Stronghold
    -0.72
     Wit
    -0.72
    Thom
    -0.72
    uble
    -0.71
     Sovere
    -0.67
    stra
    -0.63
    doi
    -0.63
    POSITIVE LOGITS
     prescribe
    1.16
     prescribing
    1.14
     prescribed
    1.08
     medications
    0.98
     medication
    0.97
     opioids
    0.93
     medicines
    0.93
     medicine
    0.89
     prescription
    0.89
     presc
    0.87
    Activations Density 0.016%

    No Known Activations