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. 3-RES-JB
    6. 10357
    Prev
    Next
    INDEX
    Explanations

    words related to the repair of various items or equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to repair services and maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.73
    ramid
    -0.71
    obar
    -0.70
     Flan
    -0.70
    azer
    -0.70
    AMY
    -0.70
    doms
    -0.68
    Justice
    -0.68
    ean
    -0.67
    oft
    -0.67
    POSITIVE LOGITS
     repair
    1.20
     repairs
    1.08
     repairing
    1.06
    repair
    1.01
    ments
    0.89
     repaired
    0.87
     salvage
    0.83
     Repair
    0.82
     maintenance
    0.79
     ashore
    0.78
    Activations Density 0.020%

    No Known Activations