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. 2-RES-JB
    6. 24497
    Prev
    Next
    INDEX
    Explanations

    the number 80 in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    statistical or numerical data points, particularly percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.71
    DragonMagazine
    -0.69
    hammad
    -0.67
    ilic
    -0.67
    folk
    -0.65
    utra
    -0.64
    parency
    -0.64
    hold
    -0.64
    ãĥ¼ãĥ³
    -0.63
    fecture
    -0.62
    POSITIVE LOGITS
    %"
    1.05
    %-
    1.01
    %
    1.00
     percent
    0.94
    %:
    0.94
    %,
    0.93
    %;
    0.92
     Minutes
    0.91
     cents
    0.91
    %.
    0.86
    Activations Density 0.091%

    No Known Activations