Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20296
    Prev
    Next
    INDEX
    Explanations

    Twitter handles containing the name "Tony"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person's name and associated social media mentions

    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
    raz
    -0.95
    raq
    -0.93
    Cra
    -0.92
     AZ
    -0.88
    chwitz
    -0.85
    aven
    -0.81
     Kazakh
    -0.80
     reef
    -0.79
     scorp
    -0.78
     dup
    -0.78
    POSITIVE LOGITS
     Thomas
    2.26
    Thomas
    2.19
     Tom
    1.55
    Tom
    1.50
     Tommy
    1.24
     TOM
    1.20
     Thom
    1.19
     Titus
    1.17
     Tomas
    1.14
     tom
    1.14
    Activations Density 0.220%

    No Known Activations