© 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. 12-RES-JB
    11. 3592
    Prev
    Next
    INDEX
    Explanations

    information related to financial corruption or legal investigations involving individuals and businesses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to financial scandals and allegations of corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Ó
    -0.93
    ï¸ı
    -0.84
    redd
    -0.80
    áµ
    -0.77
    NPR
    -0.77
    ãĥ¼ãĤ¯
    -0.76
    女
    -0.76
    norm
    -0.76
    ÙIJ
    -0.75
    STEM
    -0.74
    POSITIVE LOGITS
     bribes
    1.13
     bankrupt
    1.13
     bribery
    1.10
     yacht
    1.09
     accountant
    1.09
     lender
    1.09
     mansion
    1.08
     businessman
    1.08
     mortgage
    1.08
     mortgages
    1.08
    Activations Density 0.573%

    No Known Activations