© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23706
    Prev
    Next
    INDEX
    Explanations

    phrases related to the location "Washington."

    oai_token-act-pair · gpt-3.5-turbo

    references to the location Washington

    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
    ulously
    -0.73
    milo
    -0.72
    ogenic
    -0.70
    leness
    -0.69
    otal
    -0.69
    regular
    -0.69
    Occ
    -0.69
    cffffcc
    -0.68
    Companies
    -0.68
    unct
    -0.68
    POSITIVE LOGITS
     Capitals
    1.09
     DC
    1.06
     Monument
    1.02
     Dull
    1.00
     Redskins
    0.99
     Bridge
    0.98
     Wizards
    0.91
     Heights
    0.91
     Nationals
    0.90
     Irving
    0.88
    Activations Density 0.019%

    No Known Activations