© 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. 11-RES-JB
    11. 18584
    Prev
    Next
    INDEX
    Explanations

    the word "Of" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Of course."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dismant
    -0.59
     behaves
    -0.58
    .","
    -0.58
    ocene
    -0.57
     violates
    -0.56
     reperto
    -0.56
     ashore
    -0.56
    opus
    -0.55
     slump
    -0.55
    IST
    -0.54
    POSITIVE LOGITS
     course
    1.55
    course
    1.35
     COUR
    1.22
    sted
    1.06
     Course
    1.03
     note
    0.98
    icial
    0.98
    ortunately
    0.98
     particular
    0.93
    elia
    0.93
    Activations Density 0.027%

    No Known Activations