Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15873
    Prev
    Next
    INDEX
    Explanations

    word "lazy" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to laziness

    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
    ciation
    -0.76
    idine
    -0.74
    rity
    -0.73
    Trust
    -0.71
    icipated
    -0.70
    iations
    -0.70
    ibel
    -0.69
    ellation
    -0.68
    ilateral
    -0.67
    semble
    -0.66
    POSITIVE LOGITS
     peasants
    0.87
    glers
    0.86
     hungry
    0.76
     bum
    0.75
     lazy
    0.74
     cooks
    0.73
     Hungry
    0.73
    azy
    0.70
    zed
    0.70
    uga
    0.69
    Activations Density 0.048%

    No Known Activations