© 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 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. 14996
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pay" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to payment and costs

    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
    ãĤ¼ãĤ¦ãĤ¹
    -1.03
    rust
    -0.78
    ãĤ¬
    -0.73
    ierre
    -0.69
    è¦ļéĨĴ
    -0.68
    ãĤµ
    -0.68
    igsaw
    -0.67
    Í
    -0.67
    spect
    -0.67
    å°Ĩ
    -0.66
    POSITIVE LOGITS
     taxes
    1.12
     dearly
    1.11
     homage
    1.10
     attention
    1.03
     tribute
    0.97
     royalties
    0.96
     fees
    0.96
     Taxes
    0.94
     bribes
    0.93
     dues
    0.93
    Activations Density 0.048%

    No Known Activations