© 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. 2-RES-JB
    11. 12543
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical professions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical professions, specifically pediatrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEM
    -0.72
     Doom
    -0.67
     Charm
    -0.66
    Ill
    -0.66
    orem
    -0.65
     Bolt
    -0.63
     Magnet
    -0.63
    cru
    -0.63
     Opportunity
    -0.62
     Lovecraft
    -0.61
    POSITIVE LOGITS
    azines
    0.65
     glands
    0.65
     reserv
    0.65
    utics
    0.64
    dan
    0.64
     yogurt
    0.63
     frag
    0.62
    gary
    0.62
     relegated
    0.62
     mouths
    0.62
    Activations Density 0.000%

    No Known Activations