© 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. 4-RES-JB
    11. 20816
    Prev
    Next
    INDEX
    Explanations

    financial or monetary terms related to expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to financial expenses

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

    No Comments

    Negative Logits
    unin
    -0.90
    IPS
    -0.73
    olithic
    -0.72
    gewater
    -0.71
    redd
    -0.69
    kus
    -0.68
    azer
    -0.67
     Keller
    -0.66
    ezvous
    -0.65
    appa
    -0.65
    POSITIVE LOGITS
     incurred
    1.37
     expenses
    1.10
     reimburse
    1.00
     reimb
    0.92
     reimbursement
    0.91
    itures
    0.86
     expense
    0.86
     expenditure
    0.82
     upkeep
    0.81
     expenditures
    0.80
    Activations Density 0.016%

    No Known Activations