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. 10-RES-JB
    6. 11850
    Prev
    Next
    INDEX
    Explanations

    words related to pronunciation

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to pronunciation

    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
    isconsin
    -0.73
    ONSORED
    -0.70
    oppable
    -0.70
    development
    -0.70
    iland
    -0.69
    arte
    -0.69
    apor
    -0.68
    inventory
    -0.68
    stice
    -0.66
    isol
    -0.66
    POSITIVE LOGITS
     pronunciation
    1.26
     phon
    1.11
     spelling
    1.10
    ciation
    1.08
     vowel
    1.05
     pronounce
    1.00
     pronoun
    0.99
    unci
    0.91
     deaf
    0.90
     spelled
    0.89
    Activations Density 0.064%

    No Known Activations