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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3160
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "Jud"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jud" and its variations, related to discussions about judges or judicial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Afric
    -0.69
     Mali
    -0.66
    fields
    -0.65
    اÙĦ
    -0.65
    xon
    -0.64
    forth
    -0.64
    xual
    -0.64
    oteric
    -0.63
    ULAR
    -0.61
     Kerala
    -0.61
    POSITIVE LOGITS
    gement
    1.46
    iciary
    1.39
    gment
    1.27
    gments
    1.24
    icial
    1.24
    jud
    1.19
    icator
    1.01
     Jud
    1.00
    gements
    0.97
    ging
    0.97
    Activations Density 0.014%

    No Known Activations