© 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. 4-RES-JB
    11. 962
    Prev
    Next
    INDEX
    Explanations

    words related to political figures, particularly Secretaries or Generals such as General Mattis and General Petraeus

    oai_token-act-pair · gpt-3.5-turbo

    references to military figures and their positions

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

    No Comments

    Negative Logits
     Vul
    -0.75
     Palest
    -0.73
     Stub
    -0.66
    âĸ¬
    -0.66
    BUS
    -0.65
    Sund
    -0.64
     Constantin
    -0.64
    tails
    -0.63
    nings
    -0.62
     Illegal
    -0.62
    POSITIVE LOGITS
    enegger
    1.10
     Mattis
    0.99
    oleon
    0.88
    utenant
    0.87
    ervative
    0.85
    anamo
    0.83
    psey
    0.82
    avorite
    0.82
    dinand
    0.81
     Petraeus
    0.80
    Activations Density 0.023%

    No Known Activations