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. 10-RES-JB
    6. 23903
    Prev
    Next
    INDEX
    Explanations

    ranked military officer titles

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and titles related to military and law enforcement ranks

    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
    theless
    -0.79
    brush
    -0.61
     blur
    -0.59
    DragonMagazine
    -0.59
     doub
    -0.57
    adobe
    -0.56
     obsc
    -0.56
     rend
    -0.54
     capsule
    -0.52
     flap
    -0.52
    POSITIVE LOGITS
    .,
    1.88
    .;
    1.64
    ./
    1.53
    .:
    1.48
    .?
    1.47
    .,"
    1.35
    .),
    1.35
    .-
    1.28
    .—
    1.27
    .):
    1.22
    Activations Density 0.135%

    No Known Activations