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. 4250
    Prev
    Next
    INDEX
    Explanations

    verbs related to duration or endurance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to duration or length of time something lasts

    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
    UGC
    -0.59
     Osw
    -0.59
     CRC
    -0.56
     converter
    -0.56
    icho
    -0.55
    athetic
    -0.54
    athy
    -0.54
     Fiat
    -0.53
    ramid
    -0.53
    lopp
    -0.51
    POSITIVE LOGITS
     longer
    1.22
     forever
    1.09
     indefinitely
    1.09
     awhile
    0.95
     longest
    0.90
     decades
    0.85
     several
    0.80
     months
    0.79
     beyond
    0.78
     until
    0.77
    Activations Density 0.068%

    No Known Activations