© 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. 4-RES-JB
    11. 10253
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or governmental contexts, particularly focusing on the concept of state laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to state laws and regulations

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

    No Comments

    Negative Logits
    veyard
    -0.88
    thora
    -0.88
    poons
    -0.85
    ogle
    -0.84
    imet
    -0.76
     Maw
    -0.76
    nob
    -0.75
    ayson
    -0.75
     Austral
    -0.75
    rax
    -0.74
    POSITIVE LOGITS
     legislatures
    1.08
    wide
    0.98
     governments
    0.97
     legislators
    0.88
     officials
    0.85
     agencies
    0.82
     legislature
    0.82
     lawmakers
    0.82
     government
    0.82
     regulators
    0.82
    Activations Density 0.056%

    No Known Activations