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. 18458
    Prev
    Next
    INDEX
    Explanations

    phrases related to groups or collections

    oai_token-act-pair · gpt-3.5-turbo

    references to "pack" and related terms, indicating a focus on packaging or groupings in various contexts

    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
     obser
    -0.78
    Downloadha
    -0.71
    ãĤ´ãĥ³
    -0.71
     livest
    -0.67
     Pradesh
    -0.66
     Cald
    -0.66
    abama
    -0.64
    nesota
    -0.64
    reviewed
    -0.64
    itars
    -0.63
    POSITIVE LOGITS
    ages
    1.17
    aging
    1.15
    pack
    1.11
    agers
    1.04
    packs
    0.93
    erton
    0.92
    aged
    0.92
    ager
    0.92
    erness
    0.90
     Pack
    0.90
    Activations Density 0.021%

    No Known Activations