© 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. 0-RES-JB
    11. 13099
    Prev
    Next
    INDEX
    Explanations

    military or warfare-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to danger or risk, particularly involving explosions or fire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     territory
    -0.73
     wartime
    -0.73
     Wells
    -0.71
     P
    -0.71
     perspective
    -0.71
     U
    -0.70
     F
    -0.70
     L
    -0.70
     RBI
    -0.69
     NATO
    -0.69
    POSITIVE LOGITS
    Hunt
    1.81
    Night
    1.75
    River
    1.73
    Party
    1.71
    Cause
    1.71
    Dog
    1.70
    Mask
    1.70
    Fish
    1.69
    Based
    1.69
    Sin
    1.69
    Activations Density 0.280%

    No Known Activations