© 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. 10093
    Prev
    Next
    INDEX
    Explanations

    numbers indicating quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those relating to percentages or quantities

    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
    ettings
    -0.79
    venge
    -0.70
    velt
    -0.63
     inherit
    -0.61
    medi
    -0.60
    ebin
    -0.59
    metics
    -0.59
    neum
    -0.58
    earch
    -0.58
    plan
    -0.54
    POSITIVE LOGITS
    %
    1.57
     percent
    1.43
    %-
    1.41
    %"
    1.34
    %.
    1.27
    %,
    1.18
    %:
    1.13
    percent
    1.09
    mins
    1.09
    %)
    1.08
    Activations Density 0.161%

    No Known Activations