© 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. 6-RES-JB
    11. 22657
    Prev
    Next
    INDEX
    Explanations

    instances where agreements or commitments are made

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreements or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ults
    -0.81
    clips
    -0.72
    grain
    -0.71
    laughter
    -0.68
    bars
    -0.65
    ////////////////////////////////
    -0.65
    echo
    -0.62
     geared
    -0.62
    hots
    -0.62
    icularly
    -0.62
    POSITIVE LOGITS
     waive
    1.09
     abide
    1.03
     accept
    1.03
     cooperate
    1.03
     obey
    1.01
     submit
    0.97
     participate
    0.97
     settle
    0.96
     surrender
    0.95
     comply
    0.94
    Activations Density 0.851%

    No Known Activations