© 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. 22392
    Prev
    Next
    INDEX
    Explanations

    technical instructions and details

    oai_token-act-pair · gpt-3.5-turbo

    references to system or account changes and their impacts

    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
     vocational
    -0.69
     architects
    -0.67
    nov
    -0.65
     competitions
    -0.64
     acron
    -0.64
     ambitious
    -0.64
     modesty
    -0.64
     sophistication
    -0.64
     partnerships
    -0.63
     philanthrop
    -0.63
    POSITIVE LOGITS
     respawn
    1.25
     overwrite
    1.08
     automatically
    0.98
     reverted
    0.96
     reset
    0.96
     unchanged
    0.94
     revert
    0.94
     unaffected
    0.93
     overw
    0.93
     cached
    0.92
    Activations Density 0.753%

    No Known Activations