© 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. 9-RES-JB
    6. 1473
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations or organizations in China

    oai_token-act-pair · gpt-3.5-turbo

    information related to state-owned enterprises in China

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Santorum
    -0.85
     Arkham
    -0.84
     Amanda
    -0.82
     Bucks
    -0.80
    Plugin
    -0.77
     Montgomery
    -0.77
     Bates
    -0.77
     Leigh
    -0.76
    waukee
    -0.76
     Payton
    -0.76
    POSITIVE LOGITS
     Xi
    1.89
     China
    1.88
     Shanghai
    1.88
    ijing
    1.84
    China
    1.83
     Beijing
    1.82
     Jiang
    1.81
     Chinese
    1.80
     Xin
    1.80
     Guang
    1.77
    Activations Density 0.538%

    No Known Activations