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. 15765
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and scientific research, particularly related to volumetric capture and research publications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to volumetric technology, particularly in virtual reality 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
     Cheong
    -0.78
    riad
    -0.77
    ufact
    -0.74
    nih
    -0.71
    cause
    -0.67
    negie
    -0.65
    Introduced
    -0.65
    assetsadobe
    -0.64
    intosh
    -0.64
    behind
    -0.64
    POSITIVE LOGITS
    wagen
    1.22
    ĺ
    0.78
    ioxide
    0.78
    §
    0.73
    ³
    0.70
    Ń·
    0.70
    UME
    0.68
     iod
    0.68
    pmwiki
    0.68
     dial
    0.67
    Activations Density 0.094%

    No Known Activations