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. 11-RES-JB
    6. 19843
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual and emails or correspondence related to that individual

    oai_token-act-pair · gpt-3.5-turbo

    references to email communication and associated controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UFC
    -0.75
     Gundam
    -0.73
    agos
    -0.71
     Wrest
    -0.70
    Vision
    -0.69
     Canaver
    -0.69
     subtitle
    -0.69
    liga
    -0.68
     proverb
    -0.68
    terness
    -0.67
    POSITIVE LOGITS
     Abedin
    1.59
     Huma
    1.42
     Gmail
    1.35
     emails
    1.26
     Bleach
    1.19
     Clinton
    1.18
     server
    1.18
    clinton
    1.16
     Weiner
    1.16
     email
    1.16
    Activations Density 0.192%

    No Known Activations