© 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. 2985
    Prev
    Next
    INDEX
    Explanations

    mentions of dictators, specifically Muammar Gaddafi

    oai_token-act-pair · gpt-3.5-turbo

    the name "Muammar" in various contexts related to Gaddafi

    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
    代
    -0.84
     Aires
    -0.74
    OME
    -0.72
    EMS
    -0.71
    ĪĴ
    -0.69
    ancies
    -0.68
     Peb
    -0.67
    orer
    -0.63
    arantine
    -0.62
     Dispatch
    -0.61
    POSITIVE LOGITS
    riages
    1.05
    quez
    0.87
    ques
    0.84
    iously
    0.80
    rying
    0.79
    aneously
    0.79
    riott
    0.78
    anth
    0.77
    riage
    0.76
    itime
    0.76
    Activations Density 0.013%

    No Known Activations