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. 1-RES-JB
    6. 5631
    Prev
    Next
    INDEX
    Explanations

    professionals or businesses that specialize in various services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to specialties or areas of expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ---------
    -0.80
    riel
    -0.75
     Samp
    -0.69
     Carter
    -0.68
    iron
    -0.68
    oji
    -0.67
    mar
    -0.63
     Outer
    -0.63
     Cage
    -0.62
    Ö¼
    -0.62
    POSITIVE LOGITS
     specializes
    1.20
     specialize
    1.13
    ĸļ
    0.90
     specializing
    0.89
     mathemat
    0.87
     specialized
    0.87
    otom
    0.83
    inarily
    0.83
    cyclopedia
    0.79
    ãĤ¼ãĤ¦ãĤ¹
    0.79
    Activations Density 0.011%

    No Known Activations