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. 18923
    Prev
    Next
    INDEX
    Explanations

    terms related to legal documents and procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to formal documents or proposals discussing policies and regulations

    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
    Redd
    -0.78
    sbm
    -0.72
     Scot
    -0.69
    Chance
    -0.67
    Sym
    -0.66
     Vill
    -0.62
    é»Ĵ
    -0.61
    Scot
    -0.61
    *=-
    -0.61
    ãĤ¢ãĥ«
    -0.60
    POSITIVE LOGITS
     itself
    1.44
    's
    0.92
     herself
    0.91
     himself
    0.81
     finale
    0.77
     portion
    0.75
    wright
    0.74
     opener
    0.74
     themselves
    0.72
    keeper
    0.72
    Activations Density 0.433%

    No Known Activations