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. 12-RES-JB
    6. 14516
    Prev
    Next
    INDEX
    Explanations

    terms related to labor practices in the manufacturing industry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    themes related to labor exploitation and the impact of subcontracting in factories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deen
    -0.79
    wolves
    -0.74
     poker
    -0.73
    bnb
    -0.69
     Cassidy
    -0.67
    iscopal
    -0.67
    Card
    -0.67
    Kings
    -0.67
     Poker
    -0.67
    arks
    -0.66
    POSITIVE LOGITS
     factories
    1.92
     factory
    1.71
     manufacturing
    1.63
     textile
    1.43
     Manufacturing
    1.41
     manufacture
    1.40
    Manufact
    1.38
     manufact
    1.37
     Factory
    1.37
    manufact
    1.36
    Activations Density 0.626%

    No Known Activations