Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20849
    Prev
    Next
    INDEX
    Explanations

    mentions of the title "Captain" followed by a character or place name

    oai_token-act-pair · gpt-3.5-turbo

    references to characters with the title "Captain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olars
    -0.78
    estate
    -0.78
    IZE
    -0.72
    phony
    -0.70
     foll
    -0.69
     Nieto
    -0.69
     grains
    -0.68
    election
    -0.65
    OPLE
    -0.64
    Ohio
    -0.64
    POSITIVE LOGITS
     Captain
    3.57
    Captain
    3.17
     captain
    2.21
     Capt
    2.02
     Lieutenant
    1.95
     Colonel
    1.93
     Sergeant
    1.77
     captains
    1.77
     Admiral
    1.69
     Commander
    1.63
    Activations Density 0.012%

    No Known Activations