© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9600
    Prev
    Next
    INDEX
    Explanations

    derogatory terms and insults, particularly those related to race and gender

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.05
    3:0.05
    4:0.12
    5:0.08
    6:0.04
    7:0.07
    8:0.04
    9:0.18
    10:0.04
    11:0.18
    Negative Logits
    accompan
    -3.04
     reunion
    -3.02
     reunited
    -2.92
     transitions
    -2.91
     foundations
    -2.87
     preservation
    -2.85
     cohesion
    -2.82
     revital
    -2.80
     unification
    -2.78
     stabilization
    -2.77
    POSITIVE LOGITS
     racist
    3.94
     bigot
    3.93
     sexist
    3.92
    racist
    3.79
     bitch
    3.69
     racists
    3.65
     misogyn
    3.61
     rapist
    3.45
     slut
    3.43
     whore
    3.28
    Activations Density 0.082%

    No Known Activations