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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 8820
    Prev
    Next
    INDEX
    Explanations

    dates of establishment of various entities

    oai_token-act-pair · gpt-3.5-turbo

    references to founding years of organizations and initiatives

    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
    cing
    -0.72
    blade
    -0.71
    pport
    -0.69
    icates
    -0.67
     repeat
    -0.66
     drown
    -0.64
    uffer
    -0.64
    ardon
    -0.64
    plane
    -0.62
     blot
    -0.61
    POSITIVE LOGITS
    actionDate
    0.74
     inception
    0.73
     Herbert
    0.73
     founding
    0.71
     Kad
    0.71
     Cheong
    0.69
     Yuri
    0.66
     crowdfunding
    0.64
     shortly
    0.63
    \",
    0.63
    Activations Density 0.474%

    No Known Activations