© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23623
    Prev
    Next
    INDEX
    Explanations

    numerical fractions related to divisions or percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities that are approximately half of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.71
    Trend
    -0.70
     concess
    -0.66
    lict
    -0.63
    Thumbnail
    -0.63
     appropri
    -0.58
    incinn
    -0.58
     Rav
    -0.57
    berus
    -0.56
    hran
    -0.56
    POSITIVE LOGITS
    heartedly
    0.88
    pipe
    0.72
     dozen
    0.71
    imet
    0.69
    hearted
    0.67
    wheel
    0.66
    eworks
    0.65
     percent
    0.64
    foundland
    0.63
     horsepower
    0.62
    Activations Density 0.022%

    No Known Activations