© 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. 10-RES-JB
    11. 8171
    Prev
    Next
    INDEX
    Explanations

    references to the ability to financially afford something

    oai_token-act-pair · gpt-3.5-turbo

    references to financial capability or affordability

    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
    uesday
    -0.81
    Els
    -0.75
     earthqu
    -0.69
    swick
    -0.68
    miah
    -0.66
    doi
    -0.65
    ipop
    -0.64
    yrinth
    -0.64
    bane
    -0.63
    achu
    -0.63
    POSITIVE LOGITS
    ably
    1.01
     pricey
    0.97
     to
    0.95
     expensive
    0.92
     costly
    0.82
    expensive
    0.76
     expenses
    0.75
     upkeep
    0.75
     groceries
    0.75
     adequate
    0.72
    Activations Density 0.031%

    No Known Activations