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. 8681
    Prev
    Next
    INDEX
    Explanations

    mentions of "Troopers" from the Starship Troopers franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to "troopers" and variations of the name "Tolstoy"

    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
     linking
    -0.64
     appendix
    -0.64
     mirror
    -0.64
     arch
    -0.63
     Serial
    -0.63
     REPL
    -0.62
     Wikipedia
    -0.61
     pinch
    -0.60
     FTP
    -0.60
     derivative
    -0.59
    POSITIVE LOGITS
    opers
    4.15
    uders
    1.16
    avers
    1.11
    oppers
    1.08
    ppers
    1.07
    arers
    0.93
    orks
    0.93
    akers
    0.92
     troopers
    0.90
    opes
    0.90
    Activations Density 0.021%

    No Known Activations