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. 8-RES-JB
    6. 18299
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and fields of study, such as social sciences, pediatrics, media, neuroscience, and education

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to various academic disciplines and fields of study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afer
    -0.62
    iable
    -0.57
    lyak
    -0.56
    aga
    -0.55
    atively
    -0.55
    keye
    -0.53
    ally
    -0.53
    ombo
    -0.52
    iffe
    -0.51
    icably
    -0.51
    POSITIVE LOGITS
     etc
    1.39
    etc
    1.20
     ect
    0.85
     Miscellaneous
    0.73
     Sleeping
    0.62
     ?)
    0.62
     assorted
    0.62
    whatever
    0.56
     Flavoring
    0.55
     et
    0.55
    Activations Density 0.268%

    No Known Activations