© 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. 9-RES-JB
    11. 6866
    Prev
    Next
    INDEX
    Explanations

    mentions of military actions led by a coalition

    oai_token-act-pair · gpt-3.5-turbo
    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
    DERR
    -0.77
    iddles
    -0.76
    things
    -0.72
    thia
    -0.72
    key
    -0.71
    ubb
    -0.69
    ocrates
    -0.69
    keys
    -0.68
    hang
    -0.68
    é¾įå
    -0.68
    POSITIVE LOGITS
     coalition
    1.15
     effort
    0.94
     consortium
    0.92
     Coalition
    0.91
     efforts
    0.90
     initiative
    0.87
     alliance
    0.83
     multinational
    0.82
     airstrikes
    0.82
     boycott
    0.81
    Activations Density 0.055%

    No Known Activations