© 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. 20753
    Prev
    Next
    INDEX
    Explanations

    words related to a specific cultural or geographical identity

    oai_token-act-pair · gpt-3.5-turbo

    references to the Kansai region or its people

    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
    kefeller
    -0.92
    ADS
    -0.78
    ptive
    -0.76
    PRESS
    -0.74
     Canaver
    -0.73
     buds
    -0.73
    bable
    -0.72
    nces
    -0.70
    TY
    -0.68
    ERY
    -0.68
    POSITIVE LOGITS
    alis
    1.01
    hee
    0.98
    hip
    0.94
    hin
    0.94
    igans
    0.93
    uman
    0.90
    omal
    0.90
    laughter
    0.87
    haw
    0.83
    thood
    0.83
    Activations Density 0.015%

    No Known Activations