© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    statistics or percentages

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics related to opinions and behaviors

    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
     of
    -0.84
    of
    -0.74
     Of
    -0.68
    oft
    -0.68
     OF
    -0.65
    Of
    -0.65
    OF
    -0.56
     didnt
    -0.51
    nt
    -0.51
     :(
    -0.50
    POSITIVE LOGITS
    versible
    0.59
    untarily
    0.52
    eligible
    0.51
    lette
    0.50
    ocrates
    0.50
    enson
    0.50
    hematically
    0.47
    daq
    0.47
    illions
    0.46
    quist
    0.46
    Activations Density 1.088%

    No Known Activations