© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    words related to politics and government officials in India

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of people or places

    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
    Weiss
    -0.78
     Luthor
    -0.77
    Denver
    -0.77
    emort
    -0.75
    Philadelphia
    -0.74
    âĸĪâĸĪâĸĪâĸĪ
    -0.72
     Pittsburgh
    -0.72
     âĸĪ
    -0.71
    ARDIS
    -0.71
    Atlantic
    -0.69
    POSITIVE LOGITS
     Sabha
    1.08
    bh
    1.08
     Singh
    1.05
     Sharma
    1.03
     Bhar
    1.02
    umbai
    1.00
     Raj
    0.96
    jriwal
    0.96
    pta
    0.93
    ya
    0.93
    Activations Density 0.409%

    No Known Activations