© 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. 1-RES-JB
    11. 3427
    Prev
    Next
    INDEX
    Explanations

    words related to pharmaceuticals or medical substances

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with cannabis and pharmaceuticals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.94
     Proposition
    -0.75
     Pearce
    -0.74
    manship
    -0.73
    terms
    -0.72
     Defenders
    -0.69
    sighted
    -0.68
     Dresden
    -0.68
     Doctrine
    -0.67
    IELD
    -0.62
    POSITIVE LOGITS
    abel
    0.96
    asc
    0.94
    alez
    0.88
    elled
    0.85
    aeper
    0.85
    keyes
    0.83
    oles
    0.83
    atically
    0.82
    acco
    0.82
    ated
    0.81
    Activations Density 0.016%

    No Known Activations