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. 24473
    Prev
    Next
    INDEX
    Explanations

    mentions of high school-related terms or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to school-related contexts

    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
     nod
    -0.64
     Borg
    -0.62
     exit
    -0.61
     welcome
    -0.61
     depletion
    -0.60
     count
    -0.59
     Wrap
    -0.58
     capt
    -0.58
     pel
    -0.57
     deposition
    -0.57
    POSITIVE LOGITS
    school
    4.01
    School
    2.93
     SCHOOL
    2.25
     school
    2.17
    chool
    2.03
     School
    1.99
     schools
    1.77
     Schools
    1.77
    student
    1.56
    college
    1.51
    Activations Density 0.008%

    No Known Activations