© 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. 12353
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to physical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or contexts related to cultural or community events

    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
    emort
    -1.03
     Offensive
    -0.78
    ablishment
    -0.76
    establishment
    -0.73
    rosso
    -0.73
    redits
    -0.71
    çİĭ
    -0.71
     Announce
    -0.70
    akens
    -0.70
    ukong
    -0.69
    POSITIVE LOGITS
     twent
    0.95
     nostalg
    0.83
     rented
    0.80
    mop
    0.79
     crammed
    0.78
     rainy
    0.77
     hut
    0.76
     Sierra
    0.76
     cramped
    0.75
     farmland
    0.73
    Activations Density 1.204%

    No Known Activations