© 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. 0-RES-JB
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    references to military-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military contexts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GREEN
    -0.74
     receipts
    -0.70
     refunds
    -0.68
    Rate
    -0.66
    HB
    -0.65
     credits
    -0.65
     Grape
    -0.64
     Wrap
    -0.64
    QB
    -0.63
    esan
    -0.63
    POSITIVE LOGITS
     milit
    3.78
    clad
    1.42
     militant
    0.92
     militants
    0.90
    pac
    0.89
    arak
    0.85
     separatists
    0.84
    sold
    0.83
     diplom
    0.83
    eton
    0.82
    Activations Density 0.017%

    No Known Activations