© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 17486
    Prev
    Next
    INDEX
    Explanations

    names of people or places with specific formatting and symbols

    oai_token-act-pair · gpt-3.5-turbo

    the character or symbol "Ŀ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referen
    -0.80
    awaru
    -0.78
     exhib
    -0.68
     unim
    -0.68
     memos
    -0.67
     wra
    -0.67
    chnology
    -0.67
     unborn
    -0.66
     ultras
    -0.66
     autobiography
    -0.65
    POSITIVE LOGITS
    ļ
    0.89
    Ŀ
    0.87
    º
    0.86
    bryce
    0.85
    ÏĦ
    0.83
    SourceFile
    0.83
    ¼
    0.81
    ï¸ı
    0.80
    Ĺ
    0.80
    taboola
    0.79
    Activations Density 0.138%

    No Known Activations