© 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. 1-RES-JB
    11. 24053
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or regulatory matters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.84
    stone
    -0.82
    joy
    -0.78
    tk
    -0.77
    ience
    -0.75
    ker
    -0.75
    strap
    -0.74
    gets
    -0.73
    minster
    -0.73
     Sul
    -0.72
    POSITIVE LOGITS
     regulations
    1.15
     imposed
    1.06
     governing
    0.98
     promulg
    0.98
     prescribed
    0.92
     regulators
    0.89
     permitting
    0.89
     filings
    0.89
     exempted
    0.86
     levied
    0.84
    Activations Density 0.011%

    No Known Activations