© 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. 24247
    Prev
    Next
    INDEX
    Explanations

    words related to large physical structures, specifically dams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dams

    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
    ASY
    -0.72
     Practice
    -0.72
     Spectrum
    -0.68
     Benefits
    -0.67
     Addiction
    -0.67
     Hawth
    -0.66
     Matter
    -0.65
     Surgery
    -0.65
     Airlines
    -0.64
     Disorder
    -0.62
    POSITIVE LOGITS
     dam
    1.39
    ascus
    1.00
    dump
    0.85
    ufact
    0.85
    amaz
    0.82
     dams
    0.81
    mit
    0.80
    wall
    0.80
    iets
    0.76
    riet
    0.75
    Activations Density 0.007%

    No Known Activations