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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 5802
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Judge"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Jud" or related judicial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Afric
    -0.65
    oteric
    -0.64
    ULAR
    -0.62
     Dak
    -0.62
    forth
    -0.61
    fields
    -0.61
     Horus
    -0.60
    OPLE
    -0.60
     Alz
    -0.60
     Archdemon
    -0.59
    POSITIVE LOGITS
    gement
    1.44
    iciary
    1.41
    gments
    1.31
    gment
    1.30
    icial
    1.26
    jud
    1.13
    ging
    1.04
    gements
    1.04
    iced
    1.00
    icator
    0.99
    Activations Density 0.027%

    No Known Activations