© 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. 1-RES-JB
    11. 14548
    Prev
    Next
    INDEX
    Explanations

    specific mentions of military and organizational units, particularly focusing on the term "corps" and "brigade."

    oai_token-act-pair · gpt-3.5-turbo

    references to military units or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iances
    -0.69
    ocaust
    -0.69
     refere
    -0.66
    owing
    -0.62
    _-
    -0.60
     redistributed
    -0.59
    Accessory
    -0.58
     Islamic
    -0.57
     Osama
    -0.57
    oys
    -0.56
    POSITIVE LOGITS
     corps
    1.43
    naire
    1.04
     Corps
    1.01
    kies
    0.89
    chwitz
    0.89
    wagon
    0.89
    naires
    0.84
    ngth
    0.83
    ername
    0.83
    esan
    0.82
    Activations Density 0.005%

    No Known Activations