© 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. 11-RES-JB
    11. 15004
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and coping mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mainstream media and its impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸº
    -0.70
    .:
    -0.64
    ļéĨĴ
    -0.59
    .?
    -0.58
    _.
    -0.55
    âĸł
    -0.54
     âĹı
    -0.53
     âĸ
    -0.53
    .;
    -0.52
    .-
    -0.51
    POSITIVE LOGITS
     lately
    0.58
     Keynes
    0.56
     geek
    0.54
     Canaver
    0.53
     obsess
    0.52
     understandably
    0.52
     celebrating
    0.51
     fascinated
    0.51
     rightly
    0.51
     rightfully
    0.50
    Activations Density 1.524%

    No Known Activations