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. 22143
    Prev
    Next
    INDEX
    Explanations

    phrases comparing or contrasting different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" in various contexts, often indicating comparison or relation

    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
     showc
    -0.77
     ende
    -0.74
     traged
    -0.69
     pestic
    -0.69
     cryst
    -0.69
     reperto
    -0.68
     livest
    -0.68
     misunder
    -0.68
    isively
    -0.65
     revol
    -0.64
    POSITIVE LOGITS
    icial
    0.82
    mund
    0.74
     course
    0.71
    tains
    0.69
     ordinary
    0.68
    ramer
    0.66
    course
    0.64
     Brill
    0.63
    Ħ
    0.63
    ¢
    0.63
    Activations Density 0.054%

    No Known Activations