© 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. 10-RES-JB
    11. 16120
    Prev
    Next
    INDEX
    Explanations

    specific instances of phrases that start with "the" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency repeated use 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.88
    TAIN
    -0.76
    ault
    -0.75
    911
    -0.75
    ghazi
    -0.74
    thood
    -0.72
    代
    -0.72
    plete
    -0.72
    but
    -0.72
    Guest
    -0.71
    POSITIVE LOGITS
     sheer
    1.29
     reality
    1.25
     gist
    1.22
     fact
    1.21
     downside
    1.16
     truth
    1.16
     specifics
    1.16
     ramifications
    1.14
     particulars
    1.14
     realities
    1.12
    Activations Density 0.214%

    No Known Activations