© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10126
    Prev
    Next
    INDEX
    Explanations

    legal terms related to appeals and court decisions

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases related to appeals and court rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cov
    -0.71
    enaries
    -0.71
    hin
    -0.71
    Haunted
    -0.69
     eleph
    -0.69
     Talks
    -0.68
    ubric
    -0.67
     Medline
    -0.66
    ETS
    -0.66
    hidden
    -0.65
    POSITIVE LOGITS
     ruling
    1.61
     decision
    1.59
     verdict
    1.45
     rulings
    1.44
     judgment
    1.39
     judgement
    1.36
     injunction
    1.27
     decisions
    1.22
     conviction
    1.21
     rejection
    1.20
    Activations Density 0.231%

    No Known Activations