© 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. 9-RES-JB
    11. 17051
    Prev
    Next
    INDEX
    Explanations

    locations, specifically cities and states

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.73
    requency
    -0.67
    naissance
    -0.64
    icester
    -0.64
    uggest
    -0.62
    hement
    -0.60
     Emin
    -0.60
    oldemort
    -0.59
    neapolis
    -0.59
     deposition
    -0.59
    POSITIVE LOGITS
     taxpayers
    1.11
     citizens
    1.01
    ians
    0.95
     residents
    0.92
     GDP
    0.87
     consumers
    0.85
    ans
    0.81
     Residents
    0.77
     taxpayer
    0.77
    icans
    0.76
    Activations Density 0.386%

    No Known Activations