© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 19659
    Prev
    Next
    INDEX
    Explanations

    words related to import/export activities, particularly focusing on the action of exporting and the goods being exported

    oai_token-act-pair · gpt-3.5-turbo

    references to exports and the goods associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gression
    -0.83
    soType
    -0.83
    pause
    -0.79
    Parents
    -0.75
    soDeliveryDate
    -0.75
    FontSize
    -0.75
    iseum
    -0.75
    ociation
    -0.72
    Gate
    -0.71
    ventus
    -0.71
    POSITIVE LOGITS
     goods
    1.44
     commodities
    1.23
     medicines
    1.14
     manufactured
    1.07
     products
    1.06
     wheat
    1.05
     minerals
    1.05
     Goods
    1.04
     ivory
    1.04
     imported
    1.04
    Activations Density 0.344%

    No Known Activations