© 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. 4606
    Prev
    Next
    INDEX
    Explanations

    words related to governmental and intelligence activities

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions or statements

    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
     masc
    -1.04
    mble
    -0.87
    estival
    -0.86
    æ©
    -0.85
    âĸ¬
    -0.83
    orest
    -0.80
     cider
    -0.79
    Ö
    -0.79
    iculture
    -0.77
    ocial
    -0.76
    POSITIVE LOGITS
     declass
    1.94
     CIA
    1.72
     Pentagon
    1.71
    CIA
    1.68
     Clapper
    1.67
     Cheney
    1.57
     Petraeus
    1.54
     Kissinger
    1.47
     DOD
    1.46
     Congressional
    1.42
    Activations Density 0.907%

    No Known Activations