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. 4-RES-JB
    6. 15098
    Prev
    Next
    INDEX
    Explanations

    words related to customs and legal processes

    oai_token-act-pair · gpt-3.5-turbo

    references to customs and customs duties

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

    No Comments

    Negative Logits
    ynasty
    -0.82
    ¥µ
    -0.76
    thritis
    -0.72
    icycle
    -0.72
    gets
    -0.70
    iblical
    -0.67
     Hundred
    -0.66
     CrossRef
    -0.65
    ĪĴ
    -0.65
    cki
    -0.62
    POSITIVE LOGITS
     customs
    0.99
     Customs
    0.91
     clearance
    0.86
     Enforcement
    0.85
     inspectors
    0.81
     duty
    0.80
     enforcement
    0.79
     authorities
    0.78
     officers
    0.76
     duties
    0.75
    Activations Density 0.013%

    No Known Activations