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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8333
    Prev
    Next
    INDEX
    Explanations

    mentions of armed forces

    oai_token-act-pair · gpt-3.5-turbo
    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
    Hop
    -0.84
    Bird
    -0.74
    nder
    -0.71
    STER
    -0.70
     Bout
    -0.69
    Knight
    -0.69
    CAST
    -0.68
    Shot
    -0.68
     Lamar
    -0.67
    Acknowled
    -0.66
    POSITIVE LOGITS
     forces
    1.00
     troops
    0.96
    ynski
    0.91
     fatig
    0.90
     stationed
    0.90
    forces
    0.88
     colonel
    0.87
     deployed
    0.87
     force
    0.86
    merga
    0.84
    Activations Density 0.023%

    No Known Activations