© 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. 8-RES-JB
    11. 357
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and treatment

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms and concepts related to health and genetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •contextual features
    fires on single-tokens of medical terms like " mutations" and " genetic" and " hypothesis"
    •single token firings
    fires strongly on 'rontal' (in Prefrontal) and other medical terms, and that relates to these longer contexts

    No Comments

    Negative Logits
     Vaugh
    -0.75
    deal
    -0.64
    gallery
    -0.64
    soDeliveryDate
    -0.64
    Finish
    -0.63
    orld
    -0.61
    aturdays
    -0.61
     princ
    -0.61
    ¢
    -0.60
     blat
    -0.60
    POSITIVE LOGITS
     biomark
    0.96
     cannabinoid
    0.93
     genome
    0.90
     metabolic
    0.90
     lipid
    0.90
     epigen
    0.90
     neural
    0.89
     neurot
    0.88
     circadian
    0.88
     allele
    0.88
    Activations Density 0.894%

    No Known Activations