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. 8-RES-JB
    6. 19987
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial concepts and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal or official proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nightly
    -0.88
     coral
    -0.80
     swe
    -0.78
     taste
    -0.78
     thrill
    -0.77
     dance
    -0.77
     goalie
    -0.75
     dynam
    -0.75
     fancy
    -0.74
     butterflies
    -0.74
    POSITIVE LOGITS
    According
    1.64
    Regarding
    1.60
    However
    1.54
    Furthermore
    1.54
    Moreover
    1.48
    Asked
    1.47
    Advertisement
    1.45
    Comment
    1.45
    Nevertheless
    1.43
    Section
    1.43
    Activations Density 0.561%

    No Known Activations