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. 11-RES-JB
    6. 7292
    Prev
    Next
    INDEX
    Explanations

    the word stem "ur" at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    the word "ur" or its variations, indicating a focus on a specific phrasing or slang

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otle
    -0.69
     pleas
    -0.66
     pleasing
    -0.62
    eas
    -0.61
     Benedict
    -0.59
     faithful
    -0.58
     Zucker
    -0.57
    e
    -0.57
     Feder
    -0.55
     least
    -0.54
    POSITIVE LOGITS
    geon
    1.40
    ricane
    1.18
    geons
    1.18
    thur
    1.08
    ricanes
    1.05
    iosity
    1.00
    rences
    1.00
    assic
    0.97
    andom
    0.96
    idad
    0.96
    Activations Density 0.048%

    No Known Activations