© 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. 661
    Prev
    Next
    INDEX
    Explanations

    words related to surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or entities with the suffix "sel."

    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
    riad
    -0.71
    ISC
    -0.67
    ItemTracker
    -0.65
    ISO
    -0.65
     millenn
    -0.64
    ¥ŀ
    -0.62
     inev
    -0.62
    urity
    -0.62
    merce
    -0.61
     curfew
    -0.61
    POSITIVE LOGITS
    witz
    1.11
    ength
    1.10
    atan
    1.09
    enger
    1.00
    arin
    0.98
    ibrary
    0.97
    mann
    0.95
    mas
    0.90
    ary
    0.87
    horn
    0.86
    Activations Density 0.009%

    No Known Activations