© 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 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. 7448
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Washington."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 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
    ãĥł
    -0.67
    cible
    -0.62
    antha
    -0.59
    oat
    -0.59
    adic
    -0.58
     nearest
    -0.57
    arching
    -0.57
     trophies
    -0.56
    innacle
    -0.56
    formation
    -0.55
    POSITIVE LOGITS
     CITY
    1.25
     âĢķ
    1.19
     COUNTY
    1.09
    WASHINGTON
    1.07
    ASHINGTON
    1.06
     —
    1.00
    VILLE
    0.99
    BUR
    0.98
    )—
    0.96
    EMENT
    0.96
    Activations Density 0.027%

    No Known Activations