© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4118
    Prev
    Next
    INDEX
    Explanations

    terms related to military presence and military activities, specifically in Iraq

    oai_token-act-pair · gpt-3.5-turbo

    references to military presence and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buggy
    -0.66
     reload
    -0.66
    lag
    -0.64
     Clip
    -0.64
     Mehran
    -0.64
     Pinball
    -0.63
    Revolution
    -0.62
    Mom
    -0.61
     arcade
    -0.60
    Amazing
    -0.59
    POSITIVE LOGITS
     categories
    1.49
     category
    1.43
     criteria
    1.30
     classification
    1.29
     designation
    1.25
     categor
    1.19
     excludes
    1.18
     categorized
    1.16
     definitions
    1.15
    category
    1.13
    Activations Density 0.963%

    No Known Activations