Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12020
    Prev
    Next
    INDEX
    Explanations

    Terminology related to scientific research and potential medical applications

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to medical research and its implications for treatments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Corinth
    -0.73
     POV
    -0.68
     Franch
    -0.66
     Hust
    -0.64
    vc
    -0.64
    iquette
    -0.64
    lash
    -0.63
     Rampage
    -0.63
     whining
    -0.62
     Funny
    -0.62
    POSITIVE LOGITS
     biomedical
    1.33
     scientists
    1.17
     neuroscience
    1.16
     therape
    1.14
     microsc
    1.11
     biologists
    1.10
     molecular
    1.09
     breakthrough
    1.07
     scientific
    1.06
     discoveries
    1.06
    Activations Density 0.749%

    No Known Activations