© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 854
    Prev
    Next
    INDEX
    Explanations

    words related to military conflicts and invasions

    oai_token-act-pair · gpt-3.5-turbo

    references to military invasions

    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
    ruff
    -0.78
    spot
    -0.74
    peer
    -0.73
    MpServer
    -0.73
    iac
    -0.72
    inguishable
    -0.68
    Scient
    -0.68
    milo
    -0.67
    rious
    -0.67
    ILLE
    -0.67
    POSITIVE LOGITS
    naires
    0.94
     into
    0.89
     force
    0.88
     armies
    0.87
     invasion
    0.86
     hordes
    0.78
     forces
    0.77
     conquering
    0.76
     INTO
    0.75
     Barbarian
    0.75
    Activations Density 0.068%

    No Known Activations