© 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. 11-RES-JB
    11. 9437
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities related to 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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.89
    emi
    -0.78
    eli
    -0.74
    irlf
    -0.73
    ãĥĥ
    -0.71
    INAL
    -0.71
    lass
    -0.71
    rious
    -0.71
    ãĥ³
    -0.67
    milo
    -0.67
    POSITIVE LOGITS
     DC
    1.63
     D
    1.34
    DC
    1.12
     Wizards
    0.98
     Washington
    0.87
     Dull
    0.86
     Jefferson
    0.85
    D
    0.84
     District
    0.83
     dc
    0.80
    Activations Density 0.052%

    No Known Activations