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. 7-RES-JB
    6. 18376
    Prev
    Next
    INDEX
    Explanations

    terms related to academic activities, particularly undergraduate studies and academic events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to educational subjects and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.77
     oath
    -0.66
    hani
    -0.65
     firsthand
    -0.65
     Gospel
    -0.62
     Mond
    -0.61
     Grain
    -0.61
     acquaintance
    -0.61
     Oaks
    -0.61
     Unt
    -0.59
    POSITIVE LOGITS
    uates
    1.47
    ulating
    1.43
    uated
    1.36
    ming
    1.36
    uation
    1.30
    ulated
    1.30
    ulative
    1.30
    ulators
    1.28
    uating
    1.28
    ting
    1.28
    Activations Density 0.081%

    No Known Activations