© 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. 10-RES-JB
    11. 3227
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use of excessive force

    oai_token-act-pair · gpt-3.5-turbo

    references to excessive or disproportionate behavior or actions

    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
    better
    -0.81
    ector
    -0.79
    stone
    -0.78
    ect
    -0.77
    imore
    -0.73
    spot
    -0.72
    herer
    -0.72
    bard
    -0.70
    stones
    -0.69
    scene
    -0.69
    POSITIVE LOGITS
     amounts
    0.99
     reliance
    0.94
     haste
    0.89
     complexity
    0.88
     burdens
    0.87
     caution
    0.87
     consumption
    0.87
     burden
    0.86
     scrutiny
    0.82
     quantities
    0.81
    Activations Density 0.061%

    No Known Activations