© 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. 4-RES-JB
    11. 4817
    Prev
    Next
    INDEX
    Explanations

    mentions of the medication "Viagra"

    oai_token-act-pair · gpt-3.5-turbo

    references to the medication Viagra

    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
    */(
    -1.13
    bread
    -0.81
     actionGroup
    -0.80
    lisher
    -0.78
    milo
    -0.74
    pherd
    -0.72
    LESS
    -0.72
    âķIJâķIJ
    -0.70
    side
    -0.67
    tons
    -0.66
    POSITIVE LOGITS
    agra
    1.07
    Vi
    1.03
    acs
    0.97
    alli
    0.95
    rology
    0.89
    ñ
    0.88
    ña
    0.87
    ager
    0.85
    azi
    0.82
    otti
    0.82
    Activations Density 0.004%

    No Known Activations