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. 11-RES-JB
    6. 17977
    Prev
    Next
    INDEX
    Explanations

    references to the NATO alliance

    oai_token-act-pair · gpt-3.5-turbo

    references to NATO and related military topics

    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
     Booker
    -0.76
     TMZ
    -0.75
    hyde
    -0.73
    handle
    -0.72
    ousel
    -0.72
     Ramirez
    -0.71
     MTA
    -0.71
     SX
    -0.67
    nit
    -0.67
     Manson
    -0.67
    POSITIVE LOGITS
     Allies
    1.13
     enlarg
    1.08
     allies
    1.06
     countries
    1.01
     nations
    1.00
     membership
    1.00
     member
    0.99
     ally
    0.96
     alliance
    0.96
     NATO
    0.95
    Activations Density 0.032%

    No Known Activations