© 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. 3-RES-JB
    11. 1832
    Prev
    Next
    INDEX
    Explanations

    mentions of specific medications and medical conditions, specifically focusing on "zac", "agra", "pentagram", and "Rio Grande"

    oai_token-act-pair · gpt-3.5-turbo

    references to the drug Prozac and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adin
    -0.82
    ERG
    -0.81
     Chong
    -0.77
    erving
    -0.70
    ector
    -0.68
    ERN
    -0.68
    hold
    -0.68
    SN
    -0.68
    erves
    -0.66
    erved
    -0.65
    POSITIVE LOGITS
    urations
    0.89
    uyomi
    0.87
    uration
    0.85
    代
    0.79
    xual
    0.79
     cathedral
    0.78
    isons
    0.78
    ansion
    0.77
    uese
    0.76
    agne
    0.75
    Activations Density 0.056%

    No Known Activations