© 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. 6-RES-JB
    11. 9366
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, specifically "Oakland."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Oakland."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.93
    orsche
    -0.79
    pard
    -0.78
    thood
    -0.76
    gey
    -0.75
    SHIP
    -0.74
    ivably
    -0.73
    ittance
    -0.73
    kas
    -0.72
    htaking
    -0.71
    POSITIVE LOGITS
     Raiders
    1.06
     Tribune
    0.93
     County
    0.89
     Athletics
    0.86
     Heights
    0.86
     Unified
    0.85
     Hills
    0.84
     Coliseum
    0.83
     Oakland
    0.81
     City
    0.78
    Activations Density 0.015%

    No Known Activations