© 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. 11-RES-JB
    11. 10309
    Prev
    Next
    INDEX
    Explanations

    websites or URLs

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and URLs

    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
     TAMADRA
    -0.85
     Archdemon
    -0.80
     Racial
    -0.76
     Presidency
    -0.75
     Trophy
    -0.75
     Speech
    -0.75
     Apprentice
    -0.74
     Nights
    -0.74
     MFT
    -0.73
     Advertisement
    -0.73
    POSITIVE LOGITS
    google
    1.78
    microsoft
    1.61
    amazon
    1.56
    yahoo
    1.56
    apple
    1.52
    debian
    1.51
    github
    1.49
    example
    1.48
    adobe
    1.47
    apache
    1.46
    Activations Density 0.056%

    No Known Activations