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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 24051
    Prev
    Next
    INDEX
    Explanations

    words related to exchanging, swapping, and trading

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to swapping or exchanging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.78
     "$:/
    -0.73
    Loading
    -0.72
    jam
    -0.69
    backer
    -0.66
    castle
    -0.65
    loop
    -0.65
    kamp
    -0.65
    trump
    -0.65
    jet
    -0.64
    POSITIVE LOGITS
     glances
    0.96
    nil
    0.85
     vows
    0.83
     goodbye
    0.81
     parting
    0.79
     freely
    0.75
    dayName
    0.73
     roomm
    0.73
     between
    0.73
     favour
    0.72
    Activations Density 0.055%

    No Known Activations