© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory terms like laws, regulations, standards, and statutes

    oai_token-act-pair · gpt-3.5-turbo

    references to legal compliance and regulations regarding human rights

    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
    nir
    -1.01
    ihad
    -0.96
    byn
    -0.91
    adow
    -0.80
    athing
    -0.79
    blers
    -0.79
    itars
    -0.77
     gigs
    -0.75
    ebted
    -0.74
    oops
    -0.72
    POSITIVE LOGITS
     Regulations
    1.27
     statutes
    1.21
     guidelines
    1.20
     Guidelines
    1.20
     Standards
    1.19
     Rules
    1.17
     Handbook
    1.15
     Revised
    1.13
     regulations
    1.11
     Uniform
    1.10
    Activations Density 0.498%

    No Known Activations