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. 3-RES-JB
    6. 19533
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'aud' related to auditing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of auditing or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.71
    ktop
    -0.70
     Soda
    -0.70
    OPLE
    -0.69
    Trend
    -0.68
    TON
    -0.68
     Pearce
    -0.66
     Bedford
    -0.66
     Albion
    -0.64
     Spice
    -0.64
    POSITIVE LOGITS
    itors
    1.17
    acious
    1.14
    iov
    1.09
     aud
    1.08
    itions
    1.04
    iosyn
    1.02
    aciously
    0.99
    ibly
    0.97
    yssey
    0.97
    acity
    0.95
    Activations Density 0.003%

    No Known Activations