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. 4-RES-JB
    6. 8997
    Prev
    Next
    INDEX
    Explanations

    words related to software tools and technologies, especially those related to open source software

    oai_token-act-pair · gpt-3.5-turbo

    references to open-source software and systems

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

    No Comments

    Negative Logits
    iage
    -0.86
    Bey
    -0.77
     Witches
    -0.73
     Cabrera
    -0.72
    ibur
    -0.71
     Bane
    -0.68
    doms
    -0.67
    ioxide
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     Brach
    -0.65
    POSITIVE LOGITS
    open
    0.89
    office
    0.87
    SSL
    0.80
    stack
    0.73
    Frameworks
    0.72
     antioxid
    0.72
    ahead
    0.71
    compatible
    0.69
     open
    0.68
     feder
    0.67
    Activations Density 0.020%

    No Known Activations