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. 0-RES-JB
    6. 8811
    Prev
    Next
    INDEX
    Explanations

    references to specific mines or mining activities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to mining and geological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hors
    -0.75
     operatives
    -0.75
     martial
    -0.72
     sod
    -0.70
     gy
    -0.69
    icer
    -0.68
     oper
    -0.68
    erson
    -0.66
     lax
    -0.65
     cess
    -0.65
    POSITIVE LOGITS
     Waves
    2.48
     Mine
    1.62
     {{
    1.53
    {{
    1.37
     Rocks
    1.15
    Mine
    1.11
     Discover
    1.02
    izons
    1.00
    Discover
    1.00
     Sounds
    0.89
    Activations Density 0.056%

    No Known Activations