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. 12-RES-JB
    6. 14575
    Prev
    Next
    INDEX
    Explanations

    information about people, schools, and incidents related to legal cases, schools, and communities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    schools and educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     loot
    -0.74
    pmwiki
    -0.74
     substrate
    -0.73
     mate
    -0.72
     tread
    -0.71
     packaging
    -0.71
     swarm
    -0.69
     luck
    -0.69
     inval
    -0.69
     crank
    -0.68
    POSITIVE LOGITS
     Elementary
    1.64
     High
    1.52
     Secondary
    1.45
     Prepar
    1.43
     Academy
    1.35
     Middle
    1.34
     Colleg
    1.33
     College
    1.28
     Prep
    1.26
     Community
    1.25
    Activations Density 0.370%

    No Known Activations