© 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. 11-RES-JB
    6. 6737
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sale, trade, or transfer of goods or services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the sale, trade, or transfer of regulated items or substances

    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
     Nightmares
    -0.81
    utral
    -0.68
     headaches
    -0.68
    ONES
    -0.67
     bumps
    -0.61
     Qian
    -0.61
     Boss
    -0.60
    bul
    -0.60
     unanswered
    -0.59
     Joey
    -0.59
    POSITIVE LOGITS
     distribute
    1.18
     sale
    1.08
     sell
    1.03
    export
    1.00
     possession
    0.99
     lease
    0.97
     dissemin
    0.97
     possess
    0.97
     transmit
    0.96
    sale
    0.95
    Activations Density 0.125%

    No Known Activations