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. 8-RES-JB
    6. 19927
    Prev
    Next
    INDEX
    Explanations

    statistics and information related to sports and specific ranking and performance data

    oai_token-act-pair · gpt-3.5-turbo

    references to specific teams, organizations, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    depending
    -0.78
    universal
    -0.77
     oneself
    -0.74
    assian
    -0.71
    astical
    -0.70
    ãĥĥãĤ¯
    -0.67
    itious
    -0.67
    inational
    -0.65
    yss
    -0.64
    AUT
    -0.63
    POSITIVE LOGITS
     Ambassador
    0.77
     Expo
    0.74
     Coordinator
    0.71
     Association
    0.70
     Summit
    0.70
     Initiative
    0.68
     cz
    0.67
     Ltd
    0.67
     Olympia
    0.65
     Program
    0.65
    Activations Density 0.754%

    No Known Activations