© 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. 10-RES-JB
    11. 3254
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical situations and government actions

    oai_token-act-pair · gpt-3.5-turbo

    references to aggressive governmental or leadership behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Died
    -0.92
    estamp
    -0.83
    ournals
    -0.82
    Legend
    -0.72
     LIFE
    -0.68
     Amen
    -0.67
     Nirvana
    -0.67
     Norn
    -0.66
    Cause
    -0.66
     Finished
    -0.66
    POSITIVE LOGITS
     diplomacy
    1.28
     crackdown
    1.25
     rhetoric
    1.23
     aggressive
    1.21
     militar
    1.18
     counterterrorism
    1.18
     aggressively
    1.15
     repression
    1.14
     targeting
    1.13
     tactics
    1.12
    Activations Density 0.615%

    No Known Activations