© 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
    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. 11781
    Prev
    Next
    INDEX
    Explanations

    instances of the word "customs" in relation to various contexts such as customs duties, customs officials, and cultural customs

    oai_token-act-pair · gpt-3.5-turbo

    references to customs regulations and practices

    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
    ov
    -0.72
    heimer
    -0.71
    inel
    -0.70
    ola
    -0.70
    Lean
    -0.69
    olver
    -0.68
    athon
    -0.67
    erate
    -0.65
    auer
    -0.64
    lee
    -0.63
    POSITIVE LOGITS
     customs
    4.14
     Customs
    3.16
     baggage
    1.14
     tariffs
    1.12
    Custom
    1.09
     smugglers
    1.08
     tariff
    1.07
     excise
    1.06
     traditions
    1.06
     smuggling
    1.04
    Activations Density 0.025%

    No Known Activations