© 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. 6-RES-JB
    11. 13512
    Prev
    Next
    INDEX
    Explanations

    locations or places related to specific regions

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations, specifically focusing on areas with the suffix "hire."

    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
    aganda
    -0.79
    ascript
    -0.79
    aturation
    -0.77
    acs
    -0.75
    isSpecialOrderable
    -0.74
    inventoryQuantity
    -0.72
    onym
    -0.71
    iating
    -0.70
    gotten
    -0.69
    ockets
    -0.69
    POSITIVE LOGITS
    hire
    1.23
     Hath
    1.07
    shire
    1.01
     Regiment
    0.87
     County
    0.85
     Railway
    0.82
     Yard
    0.82
     Sussex
    0.80
     Crown
    0.79
     Arabia
    0.77
    Activations Density 0.037%

    No Known Activations