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. 7295
    Prev
    Next
    INDEX
    Explanations

    instances of being the first in a particular category or achieving a significant milestone

    oai_token-act-pair · gpt-3.5-turbo

    instances of groundbreaking achievements or historical firsts

    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
    Newsletter
    -0.65
     blah
    -0.62
    ernels
    -0.61
    terness
    -0.60
     sucks
    -0.59
     Favorite
    -0.58
     Eventually
    -0.58
     wonderful
    -0.58
     beware
    -0.58
    gradation
    -0.57
    POSITIVE LOGITS
    clusively
    1.04
     publicly
    0.89
     anywhere
    0.88
     explicitly
    0.82
     ever
    0.82
     remotely
    0.81
     EVER
    0.81
     openly
    0.80
     officially
    0.79
     exclusively
    0.78
    Activations Density 0.368%

    No Known Activations