© 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. 2-RES-JB
    11. 8920
    Prev
    Next
    INDEX
    Explanations

    words related to military bases and operations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military bases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bernatorial
    -0.73
    imm
    -0.69
    poll
    -0.66
    sen
    -0.66
     acknow
    -0.64
    erenn
    -0.63
     Marketable
    -0.62
     CHO
    -0.60
     pestic
    -0.60
    ilyn
    -0.60
    POSITIVE LOGITS
    gur
    0.95
    keeper
    0.84
    grounds
    0.80
    keepers
    0.78
    eers
    0.76
    nas
    0.76
    ruary
    0.75
     complexes
    0.75
    ysis
    0.75
     precinct
    0.75
    Activations Density 0.164%

    No Known Activations