© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20448
    Prev
    Next
    INDEX
    Explanations

    mentions of manufacturing facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to factories and industrial production

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.77
    GET
    -0.70
     Liberties
    -0.68
    issan
    -0.64
    ĺħ
    -0.63
     RTX
    -0.63
    izons
    -0.63
    chal
    -0.62
    ESA
    -0.62
     Graham
    -0.61
    POSITIVE LOGITS
    hops
    1.13
     factories
    1.12
     mills
    0.97
    ineries
    0.90
    inery
    0.88
     outsourcing
    0.84
    chwitz
    0.83
     factory
    0.82
     warehouses
    0.81
    ourced
    0.78
    Activations Density 0.013%

    No Known Activations