© 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. 7-RES-JB
    11. 23855
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Commonwealth."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Commonwealth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gered
    -1.03
    geon
    -0.93
    bel
    -0.88
    heet
    -0.85
    abl
    -0.84
    gers
    -0.83
    outer
    -0.82
    bing
    -0.80
    THER
    -0.80
    ño
    -0.76
    POSITIVE LOGITS
     Coliseum
    0.91
     Commonwealth
    0.88
     Edison
    0.86
     Schwarzenegger
    0.83
     Auditor
    0.72
     Highway
    0.69
     Corpus
    0.68
     Scientific
    0.68
     Sons
    0.67
     Crest
    0.66
    Activations Density 0.060%

    No Known Activations