© 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. 10-RES-JB
    11. 8147
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and service agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to terms of service and agreement

    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
    oday
    -0.81
    CENT
    -0.73
     mornings
    -0.69
    MpServer
    -0.69
    heastern
    -0.68
     Tycoon
    -0.67
    Stars
    -0.66
    zo
    -0.61
     enthusi
    -0.58
     Centers
    -0.58
    POSITIVE LOGITS
     engagement
    0.99
     tenancy
    0.98
     lease
    0.94
     service
    0.93
     agreement
    0.87
     employment
    0.85
     truce
    0.84
     engagements
    0.84
     probation
    0.83
     surrender
    0.82
    Activations Density 0.043%

    No Known Activations