© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5536
    Prev
    Next
    INDEX
    Explanations

    instances of specific events or actions, particularly those related to dates or locations

    oai_token-act-pair · gpt-3.5-turbo

    verbs and activities related to important events or changes

    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
    .}
    -0.80
    .''.
    -0.76
    .�
    -0.70
    unless
    -0.67
    %.
    -0.65
     endif
    -0.65
    >.
    -0.63
    %).
    -0.63
    "!
    -0.62
    $.
    -0.62
    POSITIVE LOGITS
     yesterday
    0.89
     last
    0.80
     he
    0.77
     earlier
    0.73
    ileaks
    0.70
     she
    0.69
    ruary
    0.66
     we
    0.65
    ,[
    0.64
     there
    0.64
    Activations Density 0.666%

    No Known Activations