© 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. 11-RES-JB
    11. 14867
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    financial and legal terminology associated with agreements and compliance

    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
    govtrack
    -0.82
    oldown
    -0.80
    amiya
    -0.74
     Classics
    -0.66
     plum
    -0.62
    itton
    -0.62
     boarding
    -0.60
     busted
    -0.60
    agy
    -0.60
     Ping
    -0.60
    POSITIVE LOGITS
     Factors
    0.95
     Securities
    0.83
     Statements
    0.82
     materially
    0.81
     Activision
    0.80
     hereby
    0.79
     Company
    0.78
     uncertainties
    0.78
     assumptions
    0.77
     Unreal
    0.77
    Activations Density 0.118%

    No Known Activations