© 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. 3-RES-JB
    11. 3798
    Prev
    Next
    INDEX
    Explanations

    mentions of militant groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to various militant groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.80
    orem
    -0.75
    encers
    -0.73
    Rate
    -0.72
    eries
    -0.72
    ðĿ
    -0.72
     Spot
    -0.72
    æ©Ł
    -0.71
    uries
    -0.71
    laus
    -0.69
    POSITIVE LOGITS
     militant
    1.03
     Islamist
    0.97
     militants
    0.96
     insurgency
    0.91
     Islamists
    0.91
     insurgent
    0.83
     gunmen
    0.79
     milit
    0.79
     gunman
    0.79
     jihadist
    0.78
    Activations Density 0.015%

    No Known Activations