Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18327
    Prev
    Next
    INDEX
    Explanations

    words related to education, graduation, and academic achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to graduation and educational attainment

    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
    erness
    -0.71
    eur
    -0.63
    pers
    -0.62
    matic
    -0.61
    rors
    -0.61
    some
    -0.60
    opus
    -0.59
    ensen
    -0.59
     amplification
    -0.58
     inserts
    -0.58
    POSITIVE LOGITS
     college
    0.98
    College
    0.89
     academ
    0.88
     SCHOOL
    0.83
     College
    0.83
    college
    0.83
     from
    0.82
     kindergarten
    0.75
     university
    0.75
     victorious
    0.73
    Activations Density 0.059%

    No Known Activations