© 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. 4-RES-JB
    11. 98
    Prev
    Next
    INDEX
    Explanations

    names with the string "ela" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ela" or references to 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rations
    -0.85
    liners
    -0.71
    dinand
    -0.71
    rider
    -0.70
    teenth
    -0.69
    warts
    -0.69
    rat
    -0.68
    race
    -0.67
    hemat
    -0.67
    emporary
    -0.67
    POSITIVE LOGITS
     Mae
    0.86
    uthor
    0.79
    velength
    0.79
    udi
    0.79
     Merkel
    0.76
     Mandela
    0.76
    zyk
    0.75
    emon
    0.73
    eno
    0.73
    ena
    0.72
    Activations Density 0.007%

    No Known Activations