© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4941
    Prev
    Next
    INDEX
    Explanations

    references to official letters or communications

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instances of the word "letter" referring to written communications or documents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    olve
    -0.79
    olves
    -0.72
    rises
    -0.61
    illian
    -0.58
    ptions
    -0.57
    ccording
    -0.57
    ESCO
    -0.56
    ohl
    -0.55
    olved
    -0.55
     eclipse
    -0.55
    POSITIVE LOGITS
    head
    1.01
     addressed
    1.00
     dated
    0.98
    boxing
    0.94
     requesting
    0.89
     penned
    0.85
     informing
    0.84
     sent
    0.84
     outlining
    0.83
     criticizing
    0.81
    Activations Density 0.093%

    No Known Activations