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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3300
    Prev
    Next
    INDEX
    Explanations

    words related to government and regulatory agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental and regulatory entities and concepts related to law and public policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.84
     herds
    -0.72
     bunk
    -0.71
     pupils
    -0.70
     separat
    -0.69
     pse
    -0.69
     flatt
    -0.69
     trek
    -0.68
     chains
    -0.67
     favourites
    -0.67
    POSITIVE LOGITS
     Accountability
    1.33
     Regulatory
    1.23
     Advisory
    1.20
     Bureau
    1.16
     Commission
    1.16
     Department
    1.16
     Committee
    1.14
     Assistance
    1.10
     Subcommittee
    1.10
     Protection
    1.10
    Activations Density 0.215%

    No Known Activations