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. 3-RES-JB
    6. 2473
    Prev
    Next
    INDEX
    Explanations

    keywords related to the field of education and educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Education" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vati
    -0.81
    warts
    -0.72
    ificent
    -0.72
    ifully
    -0.71
    apache
    -0.71
    aunder
    -0.70
    76561
    -0.68
    alcohol
    -0.67
    amy
    -0.67
    ocial
    -0.66
    POSITIVE LOGITS
     Matters
    0.97
     Systems
    0.96
     Matter
    0.94
     Management
    0.93
     Supplement
    0.93
     Assistance
    0.92
     Directorate
    0.92
     Franch
    0.91
     Fund
    0.90
     Agent
    0.88
    Activations Density 0.046%

    No Known Activations