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. 3-RES-JB
    6. 8659
    Prev
    Next
    INDEX
    Explanations

    numerical values that are in the high end of the range

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.81
    urus
    -0.71
    imaru
    -0.67
    uyomi
    -0.66
    folk
    -0.65
    DragonMagazine
    -0.62
    venant
    -0.61
    achu
    -0.60
    ãĥ¼ãĥ³
    -0.60
     administr
    -0.59
    POSITIVE LOGITS
    %"
    1.07
    %
    1.06
    %,
    1.03
    %-
    1.00
     percent
    0.96
    %.
    0.95
    th
    0.91
    %:
    0.90
     stitches
    0.89
    ¢
    0.88
    Activations Density 0.159%

    No Known Activations