Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23244
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    adverbial forms indicating frequency or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arth
    -0.98
    ipedia
    -0.86
    arna
    -0.78
    wikipedia
    -0.73
    href
    -0.73
    yp
    -0.72
     Metall
    -0.72
    trap
    -0.71
    ARI
    -0.71
    wright
    -0.71
    POSITIVE LOGITS
     equivalents
    0.82
     endeavour
    0.82
    ²¾
    0.82
     visitation
    0.81
     endeavor
    0.80
     continuation
    0.79
     custody
    0.78
     affairs
    0.78
     pursuits
    0.78
     communication
    0.77
    Activations Density 0.094%

    No Known Activations