© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13365
    Prev
    Next
    INDEX
    Explanations

    technical terms related to financial and economic aspects, particularly focusing on value-added tax (VAT) and gross domestic product (GDP)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to taxes, economic metrics, and technology specifications

    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
    flies
    -0.82
     ç¥ŀ
    -0.75
    court
    -0.73
    theless
    -0.72
    fold
    -0.72
    folk
    -0.71
    chester
    -0.70
    arians
    -0.69
    lies
    -0.69
    atom
    -0.69
    POSITIVE LOGITS
    s
    1.17
    Os
    1.14
    Ps
    1.10
    Ds
    1.09
    Cs
    1.03
    Vs
    1.03
    Ms
    1.03
    IL
    0.99
    Bs
    0.99
    Ts
    0.98
    Activations Density 0.193%

    No Known Activations