© 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. 8-RES-JB
    11. 3390
    Prev
    Next
    INDEX
    Explanations

    numerical values presented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to product specifications and details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Augusta
    -0.75
     Flores
    -0.72
     Hammond
    -0.71
     Kol
    -0.70
    hole
    -0.68
     Grace
    -0.68
     humid
    -0.68
     hol
    -0.67
     Rowe
    -0.66
     Mississ
    -0.66
    POSITIVE LOGITS
    3
    1.29
     3
    1.09
     III
    1.04
    ĭ
    0.90
    03
    0.86
    III
    0.83
     Three
    0.82
    three
    0.80
    4
    0.79
     03
    0.77
    Activations Density 0.218%

    No Known Activations