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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 17501
    Prev
    Next
    INDEX
    Explanations

    words related to pronunciation or being pronounced

    oai_token-act-pair · gpt-3.5-turbo

    words related to pronunciation or ways to articulate terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aldo
    -0.77
    anova
    -0.74
    Constructed
    -0.71
    ivals
    -0.70
    ansas
    -0.70
    Joined
    -0.68
     Investig
    -0.67
    arte
    -0.66
    art
    -0.65
     Created
    -0.64
    POSITIVE LOGITS
     pronunciation
    1.02
     spelling
    0.95
     deaf
    0.94
     vowel
    0.90
     aloud
    0.89
     pronounce
    0.87
     phon
    0.83
    ciation
    0.83
     doom
    0.82
    ysis
    0.82
    Activations Density 0.064%

    No Known Activations