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. 15418
    Prev
    Next
    INDEX
    Explanations

    names of influential figures in the tech industry and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent figures in the tech industry, particularly those involved in venture capital and startups

    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
     Staten
    -0.83
     deport
    -0.81
     provincial
    -0.74
     barracks
    -0.72
     Isles
    -0.71
     conflicting
    -0.69
     poss
    -0.68
     dism
    -0.67
     shelters
    -0.66
    population
    -0.65
    POSITIVE LOGITS
     Labs
    1.12
    ertodd
    0.96
     Developers
    0.90
    Shares
    0.88
    Found
    0.88
     Ventures
    0.87
    Bench
    0.86
    Intel
    0.86
    Crypt
    0.84
     Silicon
    0.83
    Activations Density 0.208%

    No Known Activations