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. 16401
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures and first aid actions involving bandages and wrapping

    oai_token-act-pair · gpt-3.5-turbo

    references to wrapping and binding, especially in medical or protective contexts

    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
    ovie
    -0.90
    =-=-=-=-
    -0.79
    ITNESS
    -0.79
    Hunt
    -0.77
    Tax
    -0.72
    âĹ¼
    -0.72
    Reports
    -0.69
    SPONSORED
    -0.68
     Taxes
    -0.68
    capital
    -0.67
    POSITIVE LOGITS
     cloth
    1.60
     sleeve
    1.44
     sleeves
    1.44
    cloth
    1.38
     coat
    1.26
     jacket
    1.25
     coated
    1.25
     straps
    1.23
     draped
    1.22
     gown
    1.21
    Activations Density 0.555%

    No Known Activations