© 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. 8-RES-JB
    11. 10353
    Prev
    Next
    INDEX
    Explanations

    negative labels or accusations about individuals

    oai_token-act-pair · gpt-3.5-turbo

    labels and accusations related to negative societal judgments and prejudices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rises
    -0.74
     Administ
    -0.74
    mares
    -0.66
    ispers
    -0.66
    tails
    -0.65
     Adren
    -0.62
    riott
    -0.60
    kell
    -0.59
    amara
    -0.58
    asio
    -0.58
    POSITIVE LOGITS
     because
    0.88
     unworthy
    0.82
    .[
    0.76
     deserving
    0.75
     punishable
    0.71
     undermin
    0.71
     due
    0.69
     owing
    0.68
    because
    0.68
    ,[
    0.67
    Activations Density 0.423%

    No Known Activations