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. 0-RES-JB
    6. 8729
    Prev
    Next
    INDEX
    Explanations

    mentions of organic substances or medical fields related to healthcare

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organic substances and medical/health-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ferry
    -0.76
     ferry
    -0.75
     cru
    -0.71
     epist
    -0.66
     bridges
    -0.65
    Ware
    -0.64
     mistaken
    -0.64
     stra
    -0.63
     Bike
    -0.63
     Bliss
    -0.63
    POSITIVE LOGITS
    organic
    2.67
    activity
    1.76
    iatrics
    1.75
    animate
    1.66
    iatric
    1.45
     vitro
    1.28
    oup
    1.21
    clusions
    1.20
    itsch
    1.13
    activation
    1.05
    Activations Density 0.073%

    No Known Activations