© 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. 20531
    Prev
    Next
    INDEX
    Explanations

    phrases related to business agreements and deals

    oai_token-act-pair · gpt-3.5-turbo

    references to contracts and agreements in various contexts

    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
     Rebell
    -0.67
    ometimes
    -0.66
    ocaust
    -0.66
    answered
    -0.65
    iris
    -0.62
    inas
    -0.61
    acists
    -0.61
     dictators
    -0.57
    licks
    -0.57
     wakes
    -0.57
    POSITIVE LOGITS
     memorandum
    0.94
     dated
    0.85
     agreement
    0.82
     totaling
    0.81
     worth
    0.81
     to
    0.81
     for
    0.80
     authorizing
    0.79
     whereby
    0.77
    itled
    0.77
    Activations Density 0.219%

    No Known Activations