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. 11-RES-JB
    6. 19516
    Prev
    Next
    INDEX
    Explanations

    product-related information, such as prices and features

    oai_token-act-pair · gpt-3.5-turbo

    references to online shopping and product details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sucker
    -0.81
     deliber
    -0.76
     startled
    -0.76
     hust
    -0.74
     upset
    -0.73
     intrigued
    -0.73
     pos
    -0.73
     questioning
    -0.72
     spir
    -0.71
     waging
    -0.71
    POSITIVE LOGITS
     Optional
    1.21
    FAQ
    1.20
    Recommended
    1.18
    Optional
    1.15
     Includes
    1.14
    Quantity
    1.12
     Availability
    1.08
    Additional
    1.07
    Minimum
    1.07
    Includes
    1.06
    Activations Density 0.331%

    No Known Activations