© 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. 12461
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and numerals

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in 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
    merce
    -1.00
    puter
    -0.99
    ufact
    -0.96
    nesota
    -0.86
     adolesc
    -0.83
    ittee
    -0.79
    awaru
    -0.79
    byter
    -0.78
     satell
    -0.78
    wcs
    -0.77
    POSITIVE LOGITS
    ³
    1.13
    ت
    1.05
    ´
    1.01
    ÙĨ
    1.00
    ł
    0.99
    Ùħ
    0.90
    ï¸ı
    0.84
    л
    0.82
    µ
    0.82
    ÙĬ
    0.82
    Activations Density 0.003%

    No Known Activations