© 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. 18674
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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
    APD
    -0.82
    ghazi
    -0.81
    channelAvailability
    -0.80
    Contents
    -0.79
    ajor
    -0.78
    æĪ¦
    -0.75
    20439
    -0.75
    ettings
    -0.74
    ascus
    -0.74
    CHAPTER
    -0.74
    POSITIVE LOGITS
     idea
    1.33
     duo
    1.02
     ingenious
    1.01
     gist
    1.01
     premise
    0.97
     payoff
    0.96
     creators
    0.95
     project
    0.95
     fledgling
    0.95
     concept
    0.95
    Activations Density 0.412%

    No Known Activations