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. 6-RES-JB
    6. 15832
    Prev
    Next
    INDEX
    Explanations

    references to biological molecules, proteins, and genetic expressions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and identifiers related to biomedical research, particularly in the context of specific proteins and their markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franch
    -0.76
    Engineers
    -0.73
    Weather
    -0.73
    orld
    -0.72
    soDeliveryDate
    -0.71
    alloween
    -0.71
    Offline
    -0.69
    books
    -0.69
     Fiesta
    -0.69
    utory
    -0.68
    POSITIVE LOGITS
     receptor
    1.19
    β
    1.17
     inhibition
    1.13
     receptors
    1.12
     protein
    1.09
     proteins
    1.09
     inhibitors
    1.07
     antibody
    1.05
    α
    1.05
     mRNA
    1.05
    Activations Density 0.137%

    No Known Activations