© 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. 0-RES-JB
    11. 16949
    Prev
    Next
    INDEX
    Explanations

    phrases or entities preceded by the word "THE"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monitoring
    -0.71
     input
    -0.64
     user
    -0.64
     users
    -0.63
     values
    -0.62
     parameters
    -0.62
     unit
    -0.62
     event
    -0.61
     Ag
    -0.61
    ures
    -0.61
    POSITIVE LOGITS
    THE
    3.51
    THIS
    1.86
    WHAT
    1.75
    YOU
    1.61
    HOW
    1.57
    THER
    1.54
    TH
    1.50
     THE
    1.46
    BOOK
    1.31
    CONCLUS
    1.27
    Activations Density 0.010%

    No Known Activations