© 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. 11-RES-JB
    11. 2262
    Prev
    Next
    INDEX
    Explanations

    medical terms or medical-related terms

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to medical and regulatory topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -1.15
     oneself
    -0.82
     scout
    -0.76
     dart
    -0.76
     coupled
    -0.71
     interchange
    -0.71
     fed
    -0.71
     latter
    -0.70
     midway
    -0.69
     alternatively
    -0.69
    POSITIVE LOGITS
    uctions
    1.15
    phies
    1.11
    ifacts
    1.09
    earances
    1.08
    rupted
    1.07
    alties
    1.07
    ceptions
    1.05
    gments
    1.04
    ventions
    1.04
    ractions
    1.03
    Activations Density 0.219%

    No Known Activations