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. 10-RES-JB
    6. 3921
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific word "Jud" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jud" in various contexts, indicating references to judicial figures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULAR
    -0.70
    ription
    -0.68
    CHAT
    -0.64
     Dak
    -0.60
    اÙĦ
    -0.60
     recomm
    -0.59
    ULT
    -0.58
     Afric
    -0.57
     Ashton
    -0.57
    ISTER
    -0.56
    POSITIVE LOGITS
    gement
    1.65
    iciary
    1.59
    icial
    1.50
    gments
    1.47
    gment
    1.44
    gements
    1.31
    ging
    1.19
    icator
    1.13
    icious
    1.07
    ges
    1.07
    Activations Density 0.021%

    No Known Activations