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. 5422
    Prev
    Next
    INDEX
    Explanations

    large numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    financial statistics and numerical data

    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
     redist
    -0.68
     bail
    -0.64
    lessly
    -0.62
     loft
    -0.61
    ollah
    -0.61
     decor
    -0.61
     inaction
    -0.61
     synerg
    -0.60
     fuss
    -0.60
     lavish
    -0.60
    POSITIVE LOGITS
    bps
    0.94
     compared
    0.91
    /.
    0.84
    /,
    0.82
    %.
    0.78
    .[
    0.77
    %,
    0.77
    renheit
    0.77
    *.
    0.76
     annually
    0.76
    Activations Density 0.201%

    No Known Activations