© 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. 11-RES-JB
    11. 387
    Prev
    Next
    INDEX
    Explanations

    references to military officials and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to government positions and military personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dracula
    -0.86
    à¦
    -0.82
    alys
    -0.82
     organise
    -0.78
    estival
    -0.77
     refere
    -0.77
     Sven
    -0.76
    bnb
    -0.76
    ás
    -0.76
    bour
    -0.76
    POSITIVE LOGITS
     DOD
    2.05
     Pentagon
    2.00
     Navy
    1.88
     Marines
    1.73
     Mattis
    1.70
     USAF
    1.64
     Army
    1.59
     Defense
    1.56
    Army
    1.54
     SEAL
    1.50
    Activations Density 0.661%

    No Known Activations