© 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. 10299
    Prev
    Next
    INDEX
    Explanations

    scientific or technical processes involving various subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to "processes" in various contexts

    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
     earnest
    -0.68
    noon
    -0.67
     cheap
    -0.67
     Parables
    -0.65
     brothers
    -0.64
    gged
    -0.64
     humble
    -0.63
    rel
    -0.62
    ged
    -0.61
    rav
    -0.61
    POSITIVE LOGITS
     processes
    1.36
     process
    0.91
     Process
    0.90
    process
    0.88
    afety
    0.87
    hops
    0.85
    ctl
    0.81
     Ceres
    0.80
    Ó
    0.78
    ional
    0.76
    Activations Density 0.013%

    No Known Activations