© 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 EvalsExportsinterp-engineNEWAPI 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. 13357
    Prev
    Next
    INDEX
    Explanations

    capital letters with accents or specific symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and related statistics

    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
     occas
    -0.80
     tremend
    -0.78
     eleph
    -0.75
     thous
    -0.74
    ò
    -0.72
     exting
    -0.71
     practition
    -0.70
     hopping
    -0.69
     undermin
    -0.68
    aditional
    -0.68
    POSITIVE LOGITS
    Correct
    0.92
    ³³³
    0.87
    ↵
    0.82
    RESULTS
    0.82
    prem
    0.79
    %%
    0.78
    PHOTOS
    0.78
    Federal
    0.75
    Notable
    0.74
    Consumer
    0.73
    Activations Density 0.627%

    No Known Activations