Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10258
    Prev
    Next
    INDEX
    Explanations

    references to the number 50 or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to the number fifty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ller
    -0.81
    hunt
    -0.71
    ovie
    -0.69
    phrine
    -0.67
    worldly
    -0.66
    xual
    -0.65
    cean
    -0.63
    mble
    -0.63
    asio
    -0.63
    senal
    -0.62
    POSITIVE LOGITS
     Shades
    1.26
    ishers
    1.06
    %-
    1.01
    ¢
    0.95
    hips
    0.94
     cents
    0.93
    %"
    0.92
    Percent
    0.91
    %;
    0.89
    percent
    0.88
    Activations Density 0.041%

    No Known Activations