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. 21413
    Prev
    Next
    INDEX
    Explanations

    specific organizations, laws, and agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or acts related to governance and legal compliance

    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
    idious
    -0.87
     brim
    -0.73
     quartz
    -0.72
     toget
    -0.71
    inventoryQuantity
    -0.69
     killer
    -0.68
     headlines
    -0.67
    theless
    -0.67
     lyr
    -0.66
     slaying
    -0.66
    POSITIVE LOGITS
     Association
    1.41
     Fund
    1.30
     Associ
    1.24
     Organization
    1.22
     Organisation
    1.22
     Program
    1.20
     Commission
    1.20
     Agency
    1.19
     Programme
    1.19
     Registry
    1.18
    Activations Density 0.513%

    No Known Activations