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. 3-RES-JB
    6. 22394
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to borders or boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "fringes" or "fringe" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.89
    WARE
    -0.81
     Archdemon
    -0.74
    âĹ¼
    -0.73
    phrine
    -0.73
    uyomi
    -0.72
    LESS
    -0.72
     Twain
    -0.71
     Hots
    -0.69
    medium
    -0.68
    POSITIVE LOGITS
    inges
    1.13
    atern
    0.97
    icka
    0.94
    umpy
    0.92
    udge
    0.91
    aternal
    0.91
    isco
    0.88
    unker
    0.88
    aternity
    0.87
    aser
    0.86
    Activations Density 0.008%

    No Known Activations