© 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. 11620
    Prev
    Next
    INDEX
    Explanations

    numerical figures and percentages related to data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and financial 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
    sonian
    -0.70
    âĢ¦)
    -0.64
    hens
    -0.58
    details
    -0.57
    achine
    -0.55
    imaru
    -0.54
    letters
    -0.53
    annot
    -0.53
    oras
    -0.52
     irresist
    -0.51
    POSITIVE LOGITS
     previously
    0.99
     earlier
    0.97
     originally
    0.89
     usual
    0.87
     elsewhere
    0.85
     last
    0.81
     normally
    0.80
     ordinarily
    0.79
     initially
    0.78
     previous
    0.78
    Activations Density 0.179%

    No Known Activations