© 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. 6-RES-JB
    11. 11646
    Prev
    Next
    INDEX
    Explanations

    legal terms or court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terminology related to judicial systems and appeals courts

    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
     hint
    -0.83
     veins
    -0.77
    rouse
    -0.64
    uni
    -0.63
    ubi
    -0.63
    OTO
    -0.62
     caches
    -0.61
     thrill
    -0.61
    ãĤ£
    -0.61
    vati
    -0.61
    POSITIVE LOGITS
     Appeals
    1.01
     Justice
    0.87
     Inquiry
    0.86
     Directors
    0.84
     Settlement
    0.78
     Appeal
    0.78
     Governors
    0.76
     Commerce
    0.74
     Honour
    0.74
     Responsibility
    0.73
    Activations Density 0.061%

    No Known Activations