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. 10-RES-JB
    6. 17988
    Prev
    Next
    INDEX
    Explanations

    mentions of events or actions expected to happen in the near future

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of urgency or timing, particularly the word "sooner."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parap
    -0.68
    oft
    -0.67
     Powered
    -0.64
    etter
    -0.62
    DC
    -0.61
     Syndicate
    -0.59
    etting
    -0.59
     Shepherd
    -0.58
    orting
    -0.58
    Ward
    -0.57
    POSITIVE LOGITS
     than
    1.14
    than
    0.99
     rather
    0.99
    aneously
    0.88
     Than
    0.88
    rather
    0.84
     gratification
    0.78
    ween
    0.75
    2019
    0.74
    ths
    0.70
    Activations Density 0.049%

    No Known Activations