© 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. 8-RES-JB
    11. 410
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location (Washington, D.C.)

    oai_token-act-pair · gpt-3.5-turbo

    references to Washington, D.C

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aval
    -0.68
     actionGroup
    -0.63
     Aph
    -0.62
     Vik
    -0.60
     Prelude
    -0.59
     Polar
    -0.57
     Casual
    -0.57
    terday
    -0.57
     Lerner
    -0.57
     rede
    -0.57
    POSITIVE LOGITS
    ixie
    1.09
    WA
    0.96
    urga
    0.95
    isco
    0.94
    arts
    0.92
    ork
    0.91
    imensional
    0.89
    istant
    0.88
    etermination
    0.87
    oha
    0.84
    Activations Density 0.023%

    No Known Activations