© 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. 17462
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms or actions like rates, market capitalization, wages, deficits, salaries, pledges, and industries

    oai_token-act-pair · gpt-3.5-turbo

    financial and economic terms related to rates, wages, and market activities

    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
    interstitial
    -0.71
    çīĪ
    -0.67
    etsk
    -0.66
    urus
    -0.65
    icians
    -0.61
    kson
    -0.60
    oros
    -0.59
    ãĥŃ
    -0.59
     fault
    -0.57
    enter
    -0.57
    POSITIVE LOGITS
     considerably
    1.41
     exponentially
    1.22
     dramatically
    1.20
     significantly
    1.17
     substantially
    1.17
     drastically
    1.15
     enormously
    1.12
     tremendously
    1.12
     marginally
    1.09
     further
    1.05
    Activations Density 0.413%

    No Known Activations