© 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. 11-RES-JB
    11. 20675
    Prev
    Next
    INDEX
    Explanations

    financial terms and phrases related to monetary transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to financial responsibility and costs incurred by individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.70
    )=(
    -0.70
    vironment
    -0.67
    reprene
    -0.66
    dar
    -0.66
    thood
    -0.65
     Directory
    -0.64
    gae
    -0.64
    shine
    -0.63
    nergy
    -0.63
    POSITIVE LOGITS
     costs
    1.33
     cost
    1.26
     bills
    1.17
     expenses
    1.12
     shortfall
    1.10
     entirety
    1.09
     brunt
    1.02
     bill
    1.02
     difference
    1.01
     expense
    1.00
    Activations Density 0.116%

    No Known Activations