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. 0-RES-JB
    6. 22815
    Prev
    Next
    INDEX
    Explanations

    legal terms related to judgments and adjudication

    oai_token-act-pair · gpt-3.5-turbo

    terms related to judicial processes and the concept of judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Type
    -0.70
     containment
    -0.68
     breaks
    -0.67
     unlocks
    -0.67
     EPS
    -0.67
     ES
    -0.67
     Purdue
    -0.64
     multiple
    -0.64
     installs
    -0.63
     collapsed
    -0.63
    POSITIVE LOGITS
    jud
    4.52
    judicial
    1.67
    Jud
    1.67
     jud
    1.62
     Jud
    1.47
     judgement
    1.45
    Judge
    1.42
     judgment
    1.41
    justice
    1.37
     judge
    1.33
    Activations Density 0.009%

    No Known Activations