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

    Neuronpedia

    Jacobian LensNEW
    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. 22069
    Prev
    Next
    INDEX
    Explanations

    references to the medication "Viagra"

    oai_token-act-pair · gpt-3.5-turbo

    references to the drug Viagra

    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
    */(
    -1.02
    bread
    -0.93
    pherd
    -0.85
    milo
    -0.77
    orative
    -0.77
    binding
    -0.76
    ding
    -0.73
    raising
    -0.73
    rooms
    -0.72
    side
    -0.71
    POSITIVE LOGITS
    Vi
    1.06
     Vi
    0.96
    agra
    0.86
    acs
    0.83
    rology
    0.82
     vi
    0.82
    alli
    0.80
    isons
    0.79
    æ
    0.78
    ña
    0.75
    Activations Density 0.006%

    No Known Activations