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. 9-RES-JB
    6. 215
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial terms

    oai_token-act-pair · gpt-3.5-turbo

    any mention of the word "Jud" or variations of it, likely indicating a focus on judgments or legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dak
    -0.67
    ription
    -0.65
     Afric
    -0.63
    اÙĦ
    -0.59
     Kund
    -0.59
     Marino
    -0.58
    OPLE
    -0.58
    ULAR
    -0.57
     Metatron
    -0.56
     Horus
    -0.55
    POSITIVE LOGITS
    icial
    1.64
    iciary
    1.64
    gement
    1.55
    gment
    1.50
    gments
    1.37
    ging
    1.33
    gements
    1.20
    icator
    1.18
    ges
    1.17
    ged
    1.10
    Activations Density 0.032%

    No Known Activations