© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21144
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming

    oai_token-act-pair · gpt-3.5-turbo

    key concepts and terms related to programming or technical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obil
    -0.85
     ÂŃ
    -0.83
    Mobil
    -0.82
    vernight
    -0.77
    Thousands
    -0.73
    ordable
    -0.72
     delivered
    -0.69
     Mehran
    -0.68
    operated
    -0.68
     Tonight
    -0.66
    POSITIVE LOGITS
     analogy
    1.42
     conjecture
    1.29
     clarification
    1.24
     reasoning
    1.23
     deriv
    1.23
     definitions
    1.22
     wording
    1.22
     explanation
    1.19
     hypothesis
    1.17
     interpretation
    1.17
    Activations Density 0.788%

    No Known Activations