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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7868
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, amendments, and legal documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal statutes and constitutional amendments

    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
    pring
    -0.81
     sleeper
    -0.68
    asty
    -0.68
    elsen
    -0.67
    ilon
    -0.67
    nesday
    -0.67
    hiba
    -0.67
     Polar
    -0.66
    camp
    -0.63
     gigs
    -0.62
    POSITIVE LOGITS
     prohibitions
    1.18
     prohibits
    1.16
     repealed
    1.14
     prohibiting
    1.13
     prohibition
    1.11
     Amendments
    1.07
     outlaw
    1.07
     forbids
    1.07
     statutes
    1.04
     clauses
    1.01
    Activations Density 0.487%

    No Known Activations