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. 0-RES-JB
    6. 17607
    Prev
    Next
    INDEX
    Explanations

    references to universities or colleges

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and colleges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insert
    -0.66
     Item
    -0.65
     Tracker
    -0.63
    liction
    -0.62
    luck
    -0.62
    Item
    -0.62
    ogi
    -0.61
     Owner
    -0.61
    item
    -0.60
     filler
    -0.59
    POSITIVE LOGITS
     universities
    3.69
     Universities
    3.20
     colleges
    2.70
     campuses
    2.38
     university
    2.28
     Colleges
    2.16
     academia
    2.10
     schools
    2.05
     academics
    1.88
     museums
    1.84
    Activations Density 0.018%

    No Known Activations