Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 13426
    Prev
    Next
    INDEX
    Explanations

    keywords related to commerce and economics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pricing and market dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FontSize
    -0.85
    pause
    -0.81
     interviewer
    -0.80
    Connection
    -0.76
    axis
    -0.75
    gression
    -0.75
     Accountability
    -0.71
    iquette
    -0.70
    leader
    -0.70
     overse
    -0.70
    POSITIVE LOGITS
     goods
    1.86
     products
    1.57
     commodities
    1.56
     merchandise
    1.45
     Goods
    1.35
     items
    1.34
     medicines
    1.30
     materials
    1.23
    products
    1.22
     foods
    1.21
    Activations Density 0.649%

    No Known Activations