© 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. 0-RES-JB
    11. 18300
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal contracts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contractual agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturdays
    -0.77
     biology
    -0.76
    bledon
    -0.71
     mast
    -0.70
    peed
    -0.69
    ITE
    -0.69
    tones
    -0.68
     aback
    -0.68
     campus
    -0.65
    ãĥĻ
    -0.65
    POSITIVE LOGITS
     Contract
    2.64
     Former
    1.96
     Contracts
    1.56
    Contract
    1.41
     Construction
    1.35
     Architects
    1.27
     Prospect
    1.27
     Property
    1.25
     Position
    1.23
    contract
    1.16
    Activations Density 0.044%

    No Known Activations