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. 7321
    Prev
    Next
    INDEX
    Explanations

    ranges or intervals of numerical values

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements indicating ranges or percentages

    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
    mone
    -0.78
    lees
    -0.74
    resy
    -0.73
    orsi
    -0.73
    nor
    -0.70
    POST
    -0.69
    iquette
    -0.68
    icipated
    -0.66
    inas
    -0.66
    ppo
    -0.65
    POSITIVE LOGITS
     mildly
    0.92
     thinly
    0.77
     humorous
    0.75
     mild
    0.75
     innocuous
    0.75
     benign
    0.72
     sarcastic
    0.69
     downright
    0.69
     quirky
    0.68
     outright
    0.68
    Activations Density 0.063%

    No Known Activations