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. 2920
    Prev
    Next
    INDEX
    Explanations

    keywords related to CNC machining and related processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to manufacturing processes and machinery

    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
     yawn
    -0.72
     Chili
    -0.71
    amy
    -0.69
     epile
    -0.68
     Cele
    -0.66
     Drugs
    -0.66
     Zika
    -0.66
    onym
    -0.65
     addictive
    -0.64
    netflix
    -0.64
    POSITIVE LOGITS
     materials
    0.96
     fabrication
    0.96
    Materials
    0.95
    smanship
    0.95
     specifications
    0.91
     drawings
    0.89
     seams
    0.83
     arrang
    0.83
     layouts
    0.81
    Construction
    0.81
    Activations Density 0.323%

    No Known Activations