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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6240
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Washington"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Washington

    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
     MP
    -0.73
     cut
    -0.72
     Ap
    -0.72
     Tes
    -0.70
     Eva
    -0.69
     BB
    -0.68
     Masters
    -0.68
     AB
    -0.67
     racing
    -0.67
     breathing
    -0.66
    POSITIVE LOGITS
    Washington
    3.57
    WASHINGTON
    2.00
    Moscow
    1.52
    Denver
    1.49
    Seattle
    1.48
    ASHINGTON
    1.47
    Philadelphia
    1.41
    Baltimore
    1.40
    Wisconsin
    1.37
     Washington
    1.33
    Activations Density 0.016%

    No Known Activations