Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8574
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Shanghai" at varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city "Shanghai."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    profit
    -0.81
    gger
    -0.77
    profits
    -0.74
    ktop
    -0.73
    vous
    -0.72
    detail
    -0.71
    leck
    -0.71
    served
    -0.68
    give
    -0.68
    lete
    -0.67
    POSITIVE LOGITS
     Lumpur
    1.01
     Shanghai
    0.92
    zhou
    0.89
     Jinping
    0.88
     nood
    0.84
     Zhou
    0.82
     Shen
    0.82
    igans
    0.81
     Jiang
    0.80
     Guang
    0.78
    Activations Density 0.003%

    No Known Activations