© 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. 16114
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" followed by another word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that include the word "of."

    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
    zer
    -0.64
     partName
    -0.56
    iaries
    -0.56
    krit
    -0.56
    zers
    -0.54
    beam
    -0.54
    ynes
    -0.54
    zee
    -0.53
     violates
    -0.53
    agher
    -0.53
    POSITIVE LOGITS
     course
    1.85
     sorts
    1.72
    course
    1.44
     theirs
    1.24
     ours
    1.18
     hers
    1.18
     mine
    1.09
     yours
    1.07
     COUR
    1.06
     Course
    1.03
    Activations Density 0.252%

    No Known Activations