© 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. 10-RES-JB
    11. 20402
    Prev
    Next
    INDEX
    Explanations

    high-ranking military officials and their titles

    oai_token-act-pair · gpt-3.5-turbo

    military ranks and personnel titles

    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
    MpServer
    -0.88
     renters
    -0.81
     tenants
    -0.79
    nect
    -0.75
    roots
    -0.74
    SourceFile
    -0.73
    atown
    -0.71
    "]=>
    -0.71
     synagogue
    -0.71
     Rowling
    -0.69
    POSITIVE LOGITS
     Mattis
    1.56
     commander
    1.34
     Petraeus
    1.33
     Commander
    1.27
     Command
    1.24
     commanders
    1.22
     Admiral
    1.19
    Command
    1.17
     USAF
    1.13
     generals
    1.13
    Activations Density 0.291%

    No Known Activations