© 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. 4-RES-JB
    11. 7125
    Prev
    Next
    INDEX
    Explanations

    mentions of military terms and units such as battalions and regiments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military units and formations

    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
    plays
    -0.74
    rencies
    -0.70
    Consumer
    -0.69
    falls
    -0.64
    gets
    -0.63
     straw
    -0.63
    FACE
    -0.63
    Ven
    -0.62
    comes
    -0.62
    artz
    -0.61
    POSITIVE LOGITS
    alions
    1.47
    rons
    1.29
    alion
    1.15
     colonel
    1.09
     commander
    1.07
     regiment
    1.03
     battalion
    0.99
     stationed
    0.95
     platoon
    0.93
     commanders
    0.92
    Activations Density 0.023%

    No Known Activations