© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5416
    Prev
    Next
    INDEX
    Explanations

    references to medical pills

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "pill."

    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
     Signature
    -0.68
    Introduced
    -0.67
    atically
    -0.63
     BASE
    -0.62
     STA
    -0.62
     Fresno
    -0.61
    aton
    -0.61
     Extension
    -0.61
    henko
    -0.60
    CTV
    -0.60
    POSITIVE LOGITS
     pill
    4.16
     Pill
    2.39
    pill
    2.27
     pillow
    1.57
     pills
    1.32
     plunder
    1.16
     mattress
    1.12
     carpet
    1.06
     subjug
    0.96
     blanket
    0.93
    Activations Density 0.012%

    No Known Activations