© 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. 4-RES-JB
    11. 10576
    Prev
    Next
    INDEX
    Explanations

    references to objects or concepts with the word "of."

    oai_token-act-pair · gpt-3.5-turbo

    the word "of" in various contexts

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

    No Comments

    Negative Logits
    ilaterally
    -0.62
     vulner
    -0.62
     destro
    -0.61
     reperto
    -0.60
    ographically
    -0.60
     horizont
    -0.58
     lapt
    -0.58
    ername
    -0.56
    aturdays
    -0.54
     indic
    -0.54
    POSITIVE LOGITS
     course
    0.71
     sorts
    0.63
     SHARES
    0.56
     Tradable
    0.55
     JUSTICE
    0.54
     UNIVERS
    0.52
     BUS
    0.51
    initialized
    0.50
    cop
    0.49
     ACTION
    0.48
    Activations Density 0.074%

    No Known Activations