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. 0-RES-JB
    6. 5754
    Prev
    Next
    INDEX
    Explanations

    the word "naught" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "caught" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     br
    -0.67
     hist
    -0.66
     Section
    -0.65
     ratings
    -0.64
     Kes
    -0.63
     rating
    -0.63
     dil
    -0.62
     mood
    -0.61
     cellular
    -0.61
     Pie
    -0.61
    POSITIVE LOGITS
    aught
    4.38
    ought
    1.89
    atching
    1.24
    augh
    1.23
    omore
    0.97
    urst
    0.97
    ook
    0.97
    oded
    0.96
    aughter
    0.94
    Lear
    0.93
    Activations Density 0.005%

    No Known Activations