© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    various types of add-ons and enhancements

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and terminology related to software or programming functions

    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
     photographer
    -0.78
     newcomer
    -0.74
     lover
    -0.74
     eagle
    -0.73
     liar
    -0.73
     destroyer
    -0.71
     predator
    -0.70
     magician
    -0.70
     drummer
    -0.69
     surgeon
    -0.69
    POSITIVE LOGITS
    atures
    1.44
    encies
    1.37
    ements
    1.37
    ences
    1.37
    iques
    1.35
    gments
    1.34
    uses
    1.34
    ures
    1.33
    ages
    1.33
    ques
    1.33
    Activations Density 0.763%

    No Known Activations