© 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. 11-RES-JB
    11. 20662
    Prev
    Next
    INDEX
    Explanations

    fragments related to publication or conclusion of something, like a book or a study

    oai_token-act-pair · gpt-3.5-turbo

    statements exhibiting criticism or skepticism about social behaviors or observations

    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
    âĢ
    -1.04
     âĢ
    -0.87
     âĿ
    -0.85
    âĸº
    -0.84
     âľĶ
    -0.84
    ðŁ
    -0.83
    ðŁij
    -0.81
    ¨
    -0.79
    -0.77
    âľ
    -0.75
    POSITIVE LOGITS
     hindsight
    0.72
     Canaver
    0.72
     later
    0.71
     pity
    0.70
     1956
    0.69
     1953
    0.69
     amused
    0.69
     1935
    0.69
     Kubrick
    0.68
     1936
    0.68
    Activations Density 1.106%

    No Known Activations