© 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. 20666
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes within the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, specifically related to dates and monetary amounts

    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
    icular
    -0.75
    ãĤ¤ãĥĪ
    -0.69
    ICLE
    -0.68
    achu
    -0.64
    icles
    -0.64
     Pros
    -0.63
     Santana
    -0.63
    lier
    -0.62
    els
    -0.61
    lic
    -0.61
    POSITIVE LOGITS
     externalToEVAOnly
    0.93
    pher
    0.89
    987
    0.89
    00
    0.88
    98
    0.88
    80
    0.84
    wark
    0.81
    myra
    0.79
    989
    0.77
    57
    0.77
    Activations Density 0.120%

    No Known Activations