© 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. 17295
    Prev
    Next
    INDEX
    Explanations

    descriptions related to military settings and uniforms

    oai_token-act-pair · gpt-3.5-turbo

    references to military personnel or uniforms

    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
    DragonMagazine
    -0.70
     Learn
    -0.70
     compromises
    -0.68
    ihad
    -0.66
     setbacks
    -0.64
    estyles
    -0.63
     Comprehensive
    -0.63
    netflix
    -0.63
     taxpayers
    -0.63
     critics
    -0.62
    POSITIVE LOGITS
     staring
    1.10
     seated
    1.08
    looking
    1.08
     grinning
    1.08
     crou
    1.08
     beside
    1.04
     smir
    1.04
     glared
    1.01
     smiling
    1.01
     standing
    1.00
    Activations Density 0.538%

    No Known Activations