© 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. 8-RES-JB
    11. 6260
    Prev
    Next
    INDEX
    Explanations

    legislative and legal terminology related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to laws and legal frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rir
    -0.78
    Revolution
    -0.68
    JC
    -0.66
    wow
    -0.65
     mir
    -0.65
    iOS
    -0.64
    chet
    -0.62
     partName
    -0.61
     Simulator
    -0.61
    Beck
    -0.60
    POSITIVE LOGITS
     exceptions
    0.95
     allowable
    0.93
    shall
    0.93
     prohibitions
    0.89
     prohibits
    0.89
     forbids
    0.89
     nomine
    0.83
     punishments
    0.83
     governs
    0.82
     "[
    0.81
    Activations Density 0.419%

    No Known Activations