© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 16861
    Prev
    Next
    INDEX
    Explanations

    terms related to the production and manufacturing of various items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to various processes of production and manufacturing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idas
    -0.74
    ĸļ
    -0.72
    nee
    -0.72
    ĪĴ
    -0.67
     perv
    -0.66
    canon
    -0.65
    odon
    -0.63
    pants
    -0.62
    ikers
    -0.61
     loosen
    -0.61
    POSITIVE LOGITS
     domestically
    0.85
     batches
    0.82
     goods
    0.77
     exporting
    0.76
     quantities
    0.73
     imported
    0.73
     plants
    0.72
     shipments
    0.72
     extracts
    0.72
    redients
    0.71
    Activations Density 0.246%

    No Known Activations