© 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. 1-RES-JB
    11. 14342
    Prev
    Next
    INDEX
    Explanations

    phrases related to production or manufacturing

    oai_token-act-pair · gpt-3.5-turbo

    references to the production or manufacturing of items or substances

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    cas
    -0.79
    ede
    -0.74
    ne
    -0.73
    nton
    -0.73
    cair
    -0.71
    ser
    -0.69
    esa
    -0.69
    bi
    -0.68
    thur
    -0.67
    den
    -0.67
    POSITIVE LOGITS
    rious
    0.94
     produced
    0.85
     produces
    0.83
     outputs
    0.83
     Produ
    0.83
    smanship
    0.82
    ĸļ
    0.80
     yields
    0.79
    Output
    0.78
     produce
    0.76
    Activations Density 0.012%

    No Known Activations