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. 10-RES-JB
    6. 147
    Prev
    Next
    INDEX
    Explanations

    mentions of education

    oai_token-act-pair · gpt-3.5-turbo

    references to education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.87
    76561
    -0.69
    assis
    -0.65
    hedral
    -0.64
    onement
    -0.63
    odon
    -0.63
    ð
    -0.62
    othe
    -0.62
     Barker
    -0.62
    atra
    -0.62
    POSITIVE LOGITS
     curriculum
    1.21
     curric
    1.21
     attainment
    1.15
     vit
    0.96
     institutions
    0.95
    ally
    0.92
     instit
    0.91
     scholarships
    0.90
    Grade
    0.88
     educ
    0.87
    Activations Density 0.044%

    No Known Activations