© 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. 1-RES-JB
    11. 11356
    Prev
    Next
    INDEX
    Explanations

    percentage values in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "percentage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.82
     Horizons
    -0.79
    nee
    -0.79
    efer
    -0.73
    ãĥ«
    -0.68
    enegger
    -0.67
    ergy
    -0.66
    î
    -0.66
    ULE
    -0.66
    neys
    -0.65
    POSITIVE LOGITS
     percentage
    1.07
     percentages
    0.92
    pointer
    0.85
     Percentage
    0.84
     (%)
    0.82
    pointers
    0.79
     conversions
    0.77
    %%
    0.77
    percent
    0.73
     Percent
    0.70
    Activations Density 0.009%

    No Known Activations