Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4533
    Prev
    Next
    INDEX
    Explanations

    words related to pronunciation and spelling

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to pronunciation and spelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iland
    -0.74
    isconsin
    -0.74
    management
    -0.73
    izons
    -0.70
    hide
    -0.70
    5000
    -0.70
    aspers
    -0.69
    ebook
    -0.69
    ashtra
    -0.68
    analysis
    -0.67
    POSITIVE LOGITS
     pronunciation
    1.03
     spelling
    1.00
    ciation
    0.95
     pronoun
    0.94
     pronounce
    0.93
     phon
    0.86
     vowel
    0.85
     deaf
    0.85
     pronounced
    0.85
     conson
    0.81
    Activations Density 0.073%

    No Known Activations