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. 0-RES-JB
    6. 14032
    Prev
    Next
    INDEX
    Explanations

    expressions related to being fortunate or lucky

    oai_token-act-pair · gpt-3.5-turbo

    expressions of being fortunate or lucky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIEW
    -0.69
    ]-
    -0.67
    Export
    -0.66
    reads
    -0.65
    APD
    -0.63
     ],
    -0.62
     expressed
    -0.62
    Sep
    -0.61
     antitrust
    -0.61
     [-
    -0.61
    POSITIVE LOGITS
     lucky
    3.99
     fortunate
    3.22
     unlucky
    2.86
     luck
    1.90
     Lucky
    1.46
     blessed
    1.36
     privileged
    1.35
     thankful
    1.34
     unfortunate
    1.32
     grateful
    1.27
    Activations Density 0.014%

    No Known Activations