© 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. 11-RES-JB
    11. 20440
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and official rules

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal terminology and regulatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acus
    -0.87
    angelo
    -0.82
    auntlet
    -0.78
    cule
    -0.77
    cture
    -0.77
    undo
    -0.76
    opal
    -0.75
    wow
    -0.73
    onom
    -0.71
    NetMessage
    -0.71
    POSITIVE LOGITS
     applicants
    1.20
     employers
    1.13
     anyone
    1.12
     minors
    1.10
     individuals
    1.02
     holders
    1.01
     insurers
    1.00
     exemptions
    0.99
     businesses
    0.99
     spouses
    0.98
    Activations Density 0.332%

    No Known Activations