© 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. 6339
    Prev
    Next
    INDEX
    Explanations

    prices or discounts in various formats

    oai_token-act-pair · gpt-3.5-turbo

    prices and numerical values associated with products

    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
    igators
    -0.83
    nesota
    -0.79
    iqueness
    -0.74
    otos
    -0.73
     filibuster
    -0.71
    igating
    -0.70
    umbn
    -0.67
    igent
    -0.64
    saf
    -0.64
    istical
    -0.63
    POSITIVE LOGITS
    /$
    1.22
     USD
    0.96
    -$
    0.94
    âĤ¬
    0.86
    AU
    0.86
     cents
    0.86
    /#
    0.83
    999
    0.82
    USD
    0.78
     ($
    0.77
    Activations Density 0.031%

    No Known Activations