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. 7316
    Prev
    Next
    INDEX
    Explanations

    information related to software updates and patches

    oai_token-act-pair · gpt-3.5-turbo

    references to software updates and version changes

    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
     Hanson
    -0.81
     Berm
    -0.79
     stereotypes
    -0.78
     Heller
    -0.77
     Gardner
    -0.77
     Thiel
    -0.76
    cart
    -0.74
    agher
    -0.73
     Cathy
    -0.69
     Twain
    -0.69
    POSITIVE LOGITS
    Release
    1.41
     update
    1.41
     Release
    1.37
     fixes
    1.34
     release
    1.31
     patch
    1.27
    release
    1.25
    Version
    1.25
     Update
    1.24
    beta
    1.23
    Activations Density 0.405%

    No Known Activations