© 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. 2-RES-JB
    11. 17688
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =#
    -0.52
     thereof
    -0.52
    Ò
    -0.51
    =""
    -0.51
     apiece
    -0.50
    antes
    -0.50
     whenever
    -0.50
     signifies
    -0.50
    FontSize
    -0.50
    rand
    -0.49
    POSITIVE LOGITS
     same
    1.06
     latter
    0.96
     aforementioned
    0.89
     slightest
    0.88
     latest
    0.85
     quickest
    0.83
     fastest
    0.82
     simplest
    0.82
     vast
    0.82
    ses
    0.80
    Activations Density 1.504%

    No Known Activations