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. 10-RES-JB
    6. 13203
    Prev
    Next
    INDEX
    Explanations

    numerical data such as percentages, measurements, and currency

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isphere
    -0.71
    staking
    -0.67
    ilic
    -0.67
    ...]
    -0.66
    â̦]
    -0.65
     sealing
    -0.64
    brance
    -0.64
    rolet
    -0.63
     spoiler
    -0.62
     keeping
    -0.62
    POSITIVE LOGITS
     Months
    0.91
     Days
    0.80
     Total
    0.76
    %
    0.74
     IMAGES
    0.73
     Minutes
    0.72
     Events
    0.71
     Bed
    0.71
    nd
    0.70
    882
    0.69
    Activations Density 0.075%

    No Known Activations