© 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. 16663
    Prev
    Next
    INDEX
    Explanations

    mentions of the Air Force

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Air" in the context of aviation and military

    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
    arians
    -0.71
     reinvest
    -0.68
    enance
    -0.67
    ECT
    -0.66
    omething
    -0.65
     refere
    -0.62
    oldemort
    -0.62
    advertisement
    -0.60
     Mond
    -0.60
     reapp
    -0.59
    POSITIVE LOGITS
    plane
    1.33
    planes
    1.33
    borne
    1.13
    waves
    1.02
    ports
    0.99
    raid
    0.98
    ships
    0.97
    line
    0.96
    ship
    0.96
     Force
    0.95
    Activations Density 0.017%

    No Known Activations