© 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. 23772
    Prev
    Next
    INDEX
    Explanations

    the word "Nelson" followed by a singular name or term

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nelson" or references to significant individuals with that name

    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
    fare
    -0.86
    orical
    -0.79
    §
    -0.77
    76561
    -0.76
    ¾
    -0.74
    İ
    -0.72
    BOOK
    -0.71
    ãĤ¼
    -0.70
    Transfer
    -0.70
    ¿
    -0.69
    POSITIVE LOGITS
     Mandela
    1.48
     Nelson
    1.23
     Rockefeller
    0.89
    sey
    0.81
    otine
    0.79
    illo
    0.78
     Sau
    0.74
    elson
    0.70
     reefs
    0.70
     Cruz
    0.69
    Activations Density 0.006%

    No Known Activations