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. 20037
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the occurrence of something for the first time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "for the first time."

    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
    rez
    -0.63
    jee
    -0.62
    Reviewed
    -0.62
    rend
    -0.61
    arag
    -0.60
    amy
    -0.60
    burn
    -0.59
    MEN
    -0.59
    ico
    -0.58
    ibel
    -0.58
    POSITIVE LOGITS
     time
    1.62
    time
    1.13
     TIME
    1.09
     times
    0.99
     Time
    0.97
    TIME
    0.90
    Time
    0.86
     consecutive
    0.85
     foreseeable
    0.83
     occasion
    0.82
    Activations Density 0.048%

    No Known Activations