© 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. 18616
    Prev
    Next
    INDEX
    Explanations

    quantities or rankings related to products or markets

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various types of consumption and supply related to goods and commodities

    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
    boxing
    -0.79
    iquette
    -0.75
    Parents
    -0.74
    usra
    -0.69
    querque
    -0.68
    ĸļ
    -0.68
    dad
    -0.67
    soType
    -0.65
    nih
    -0.65
    uffle
    -0.64
    POSITIVE LOGITS
     goods
    1.43
     commodities
    1.16
     groceries
    1.06
     products
    1.03
     merchandise
    1.03
     medicines
    1.01
     Goods
    0.96
     goodies
    0.94
     food
    0.91
     tickets
    0.90
    Activations Density 0.309%

    No Known Activations