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. 9-RES-JB
    6. 22435
    Prev
    Next
    INDEX
    Explanations

    names of people, titles, and countries

    oai_token-act-pair · gpt-3.5-turbo

    proper names and titles of individuals involved in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.85
    ģĸ
    -0.78
    ¥µ
    -0.74
     Inher
    -0.62
    Ĭ±
    -0.59
    ¬¼
    -0.58
     Invention
    -0.57
     lur
    -0.57
    pmwiki
    -0.56
    iggurat
    -0.56
    POSITIVE LOGITS
     ..."
    1.37
     â̦"
    1.33
    %"
    1.25
     [
    1.24
    !"
    1.17
    ,"
    1.16
    ..."
    1.16
    .,"
    1.14
    â̦"
    1.14
    ?"
    1.13
    Activations Density 0.314%

    No Known Activations