© 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. 8-RES-JB
    11. 17605
    Prev
    Next
    INDEX
    Explanations

    words related to goods and services

    oai_token-act-pair · gpt-3.5-turbo

    references to goods and services in economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cair
    -0.73
    adian
    -0.72
    arios
    -0.67
    thia
    -0.64
     Archdemon
    -0.63
    aeda
    -0.63
    ODE
    -0.62
     Adin
    -0.60
    quist
    -0.60
    andel
    -0.59
    POSITIVE LOGITS
     goods
    1.03
     exports
    0.88
    andise
    0.88
     imports
    0.84
     shipments
    0.81
    loads
    0.81
     purchases
    0.81
    maker
    0.80
     stores
    0.80
     shipment
    0.80
    Activations Density 0.035%

    No Known Activations