© 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. 9538
    Prev
    Next
    INDEX
    Explanations

    words related to drugs and medication, specifically substances like methamphetamine and ephedrine

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "hedge."

    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
    é¾įå
    -0.70
    ISO
    -0.62
     IPA
    -0.61
     hog
    -0.59
    BIL
    -0.56
    ãĥ¯ãĥ³
    -0.56
    ilial
    -0.55
     stack
    -0.54
     context
    -0.53
    interpret
    -0.52
    POSITIVE LOGITS
    uled
    1.02
    ules
    0.91
    apeake
    0.90
    \\\\\\\\
    0.89
    tons
    0.87
    ding
    0.86
    uling
    0.83
    rina
    0.83
    gling
    0.79
    aily
    0.77
    Activations Density 0.008%

    No Known Activations