© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    references to e-books and e-commerce

    oai_token-act-pair · gpt-3.5-turbo

    terms related to e-books and digital commerce

    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
     Ran
    -0.65
     Chak
    -0.62
     lam
    -0.62
     Nek
    -0.61
     Mer
    -0.60
    sein
    -0.60
    女
    -0.60
     Haitian
    -0.59
     Sop
    -0.59
     lamb
    -0.59
    POSITIVE LOGITS
    ionage
    0.90
    ernel
    0.89
    phrine
    0.84
    naissance
    0.80
    tainment
    0.78
    eers
    0.76
    hower
    0.76
    ullivan
    0.76
    aminer
    0.75
    yright
    0.74
    Activations Density 0.081%

    No Known Activations