© 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. 3-RES-JB
    11. 9338
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial costs or expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to financial expenditures or expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbuds
    -0.74
    unin
    -0.73
    itable
    -0.73
    vironment
    -0.72
     Nether
    -0.68
    inton
    -0.68
    ently
    -0.66
    itialized
    -0.65
    IPS
    -0.65
    pload
    -0.65
    POSITIVE LOGITS
     incurred
    1.19
    umers
    1.08
     costs
    0.94
    umed
    0.94
     burden
    0.90
     burdens
    0.89
     costing
    0.86
     taxpayers
    0.84
     Costs
    0.84
     prohib
    0.83
    Activations Density 0.027%

    No Known Activations