© 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. 10-RES-JB
    11. 17528
    Prev
    Next
    INDEX
    Explanations

    numeric values structured in a specific way

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings or percentages associated with data comparisons

    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
     Flavoring
    -0.73
    anian
    -0.72
    ifax
    -0.69
    eus
    -0.67
     novelist
    -0.66
    icult
    -0.65
    imaru
    -0.65
    ey
    -0.63
    riel
    -0.61
     tension
    -0.60
    POSITIVE LOGITS
     Minutes
    1.16
    00
    1.09
    %-
    1.05
    %
    0.95
    dfx
    0.93
    fps
    0.92
    %,
    0.87
    %"
    0.82
    %;
    0.82
     cents
    0.82
    Activations Density 0.086%

    No Known Activations