© 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. 3-RES-JB
    11. 9475
    Prev
    Next
    INDEX
    Explanations

    words related to military and armed forces

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military forces and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mist
    -0.83
    BOOK
    -0.74
    âĸ¬
    -0.71
    PER
    -0.70
    Rate
    -0.70
    Bee
    -0.68
    ̶
    -0.67
    ilk
    -0.67
    Charge
    -0.65
     Thing
    -0.65
    POSITIVE LOGITS
     milit
    1.05
    arily
    0.99
    ament
    0.90
     fatig
    0.84
     reluct
    0.83
    iam
    0.80
    ifi
    0.75
    rior
    0.74
    epend
    0.74
    ancy
    0.74
    Activations Density 0.005%

    No Known Activations