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. 19411
    Prev
    Next
    INDEX
    Explanations

    words related to hard work and perseverance

    oai_token-act-pair · gpt-3.5-turbo

    references to hard work and the virtues associated with it

    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
    ãĥĺãĥ©
    -0.75
    ivil
    -0.73
     References
    -0.73
     Vend
    -0.71
    NSA
    -0.71
    Urban
    -0.71
    paralle
    -0.69
    Specific
    -0.67
    angular
    -0.67
    ĨĴ
    -0.67
    POSITIVE LOGITS
    smanship
    1.02
    manship
    0.96
     ethic
    0.92
     persever
    0.87
     diligently
    0.79
     patience
    0.75
    heet
    0.74
     gracious
    0.72
     effort
    0.70
     restoring
    0.70
    Activations Density 0.045%

    No Known Activations