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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10114
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical values with percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages related to performance metrics

    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
    hess
    -0.74
    erity
    -0.71
    achev
    -0.69
     Wilde
    -0.69
     Tycoon
    -0.68
    bilt
    -0.67
    ModLoader
    -0.67
    stri
    -0.66
    ihu
    -0.66
    redo
    -0.65
    POSITIVE LOGITS
     percent
    1.22
    %
    1.14
    %,
    1.09
    %;
    1.08
    %.
    1.07
     million
    0.91
     %
    0.91
     Percent
    0.91
    %)
    0.90
    percent
    0.89
    Activations Density 0.075%

    No Known Activations