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. 15116
    Prev
    Next
    INDEX
    Explanations

    names of individuals in news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses or textual information enclosed within parentheses

    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
     transact
    -0.75
     adjustments
    -0.72
     bump
    -0.69
     rave
    -0.69
     conver
    -0.69
     parity
    -0.68
     clin
    -0.68
     altogether
    -0.66
     procedural
    -0.65
     deem
    -0.65
    POSITIVE LOGITS
    pictured
    1.64
    left
    1.41
    above
    1.35
    Photo
    1.33
    Courtesy
    1.30
    pron
    1.26
    shown
    1.25
    bottom
    1.24
    center
    1.23
    right
    1.17
    Activations Density 0.056%

    No Known Activations