© 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. 0-RES-JB
    11. 4948
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the city of Bengaluru

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations, particularly cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ours
    -0.65
     worn
    -0.62
     draft
    -0.61
     Little
    -0.60
     plates
    -0.59
     Cub
    -0.59
     windows
    -0.59
     comed
    -0.59
     Fle
    -0.57
     Atlantic
    -0.57
    POSITIVE LOGITS
    uru
    4.65
    urus
    1.70
    iru
    1.41
    uku
    1.34
    uri
    1.23
    alore
    1.22
    ugu
    1.22
    ataka
    1.20
    urai
    1.17
    uran
    1.05
    Activations Density 0.008%

    No Known Activations