© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8933
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of customs related actions or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to customs and related regulatory concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    volent
    -0.67
     TAMADRA
    -0.67
     Panthers
    -0.66
     Hundred
    -0.66
    gets
    -0.65
    ynasty
    -0.61
     Roof
    -0.60
    OWS
    -0.59
    ASED
    -0.59
    die
    -0.59
    POSITIVE LOGITS
     customs
    1.22
     Customs
    0.93
    avorite
    0.91
    chwitz
    0.86
     handlers
    0.81
     traders
    0.75
     clearance
    0.73
     regulators
    0.72
     duties
    0.71
    afety
    0.70
    Activations Density 0.010%

    No Known Activations