© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4833
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal finances and financial struggles

    oai_token-act-pair · gpt-3.5-turbo

    references to financial situations and obligations

    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
    anguage
    -0.71
    vertisements
    -0.70
    ĸļ
    -0.70
     largeDownload
    -0.70
    isson
    -0.66
    etsk
    -0.65
    bringer
    -0.65
    ept
    -0.64
    leck
    -0.64
    agy
    -0.64
    POSITIVE LOGITS
     paycheck
    1.42
     debts
    1.28
     salary
    1.24
     savings
    1.24
     mortgage
    1.22
     income
    1.20
     earnings
    1.19
     finances
    1.19
     pension
    1.10
     employer
    1.10
    Activations Density 0.203%

    No Known Activations