© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22683
    Prev
    Next
    INDEX
    Explanations

    mentions of military ranks, such as Lieutenant Colonel and Governor

    oai_token-act-pair · gpt-3.5-turbo

    references to military ranks and titles

    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
     ful
    -0.95
    uden
    -0.64
     revolving
    -0.63
     interconnected
    -0.63
    ascript
    -0.61
     audition
    -0.61
     tremend
    -0.61
    zsche
    -0.60
     reconc
    -0.60
    olving
    -0.60
    POSITIVE LOGITS
     Colonel
    1.43
     colonel
    1.37
     Commander
    1.24
     Governor
    1.23
    utenant
    1.11
    Col
    1.08
     Gen
    1.07
     Col
    1.04
     General
    1.03
     Gov
    1.00
    Activations Density 0.036%

    No Known Activations