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. 11-RES-JB
    6. 23569
    Prev
    Next
    INDEX
    Explanations

    words related to academic subjects and degrees, specifically journalism and history

    oai_token-act-pair · gpt-3.5-turbo

    subjects related to academic fields and educational backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iband
    -0.79
    pload
    -0.71
    NetMessage
    -0.66
     Gaia
    -0.66
    lease
    -0.65
    soType
    -0.65
    annabin
    -0.63
    romeda
    -0.62
    endez
    -0.62
    76561
    -0.62
    POSITIVE LOGITS
     curriculum
    1.42
     courses
    1.40
     diploma
    1.32
     education
    1.31
     majors
    1.29
     skills
    1.28
     classes
    1.28
     curric
    1.27
     degree
    1.27
     lessons
    1.25
    Activations Density 0.245%

    No Known Activations