© 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. 13903
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating quantity or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to submissions and reports

    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
    FontSize
    -0.65
    isoft
    -0.65
     ¯
    -0.64
    lay
    -0.63
    imaru
    -0.62
    amaru
    -0.62
     Roose
    -0.62
     disadvant
    -0.61
     hers
    -0.61
     slogan
    -0.60
    POSITIVE LOGITS
    %
    0.96
    00
    0.90
     instances
    0.90
     cases
    0.88
     pairs
    0.85
     individuals
    0.84
     consecutive
    0.83
     occurrences
    0.81
    th
    0.79
     individual
    0.79
    Activations Density 0.175%

    No Known Activations