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. 22390
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or listings of items within a group

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Among" and its variations

    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
     tune
    -0.61
     anytime
    -0.60
    ipper
    -0.57
    nery
    -0.56
     recons
    -0.55
     Migration
    -0.54
     somehow
    -0.54
     IPM
    -0.53
    iltr
    -0.52
     Remastered
    -0.51
    POSITIVE LOGITS
    st
    1.45
     other
    1.14
     others
    1.10
    ī
    0.98
    Others
    0.97
    ļé
    0.95
    Īè
    0.89
     many
    0.88
     reasons
    0.87
     those
    0.85
    Activations Density 0.024%

    No Known Activations