© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1245
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city of Beijing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Beijing

    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
    vari
    -0.78
     plugins
    -0.67
    reth
    -0.66
    isode
    -0.65
    mort
    -0.63
     tornado
    -0.63
    use
    -0.61
    eder
    -0.60
     carb
    -0.59
     sod
    -0.59
    POSITIVE LOGITS
     Beijing
    3.70
    ijing
    2.30
     Shanghai
    2.28
    China
    2.21
     China
    2.18
     Pyongyang
    2.11
     Seoul
    2.10
     Islamabad
    1.95
    Chinese
    1.94
     Guang
    1.90
    Activations Density 0.011%

    No Known Activations