© 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. 1-RES-JB
    11. 3637
    Prev
    Next
    INDEX
    Explanations

    mentions of pricing information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.87
    ometown
    -0.84
    san
    -0.80
     Pom
    -0.80
    aug
    -0.79
     Doe
    -0.76
     Sul
    -0.76
     Schne
    -0.74
    enegger
    -0.71
    ald
    -0.70
    POSITIVE LOGITS
     pricing
    1.34
     prices
    1.18
     refunds
    1.05
     premiums
    1.00
     price
    0.98
     fares
    0.96
     fluctuations
    0.92
     Pricing
    0.91
     gou
    0.91
     priced
    0.90
    Activations Density 0.005%

    No Known Activations