© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    content related to negative perceptions or stereotypes

    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
    1:0.05
    2:0.07
    3:0.07
    4:0.29
    5:0.05
    6:0.06
    7:0.07
    8:0.04
    9:0.08
    10:0.04
    11:0.08
    Negative Logits
    atform
    -2.95
    ��
    -2.78
    20439
    -2.76
    "}],"
    -2.75
    urrence
    -2.73
    .","
    -2.71
    umerable
    -2.60
    ipel
    -2.59
    accompan
    -2.57
    者
    -2.54
    POSITIVE LOGITS
     shitty
    6.69
     fucking
    6.65
     shit
    6.59
     fuck
    6.37
     FUCK
    6.13
     fuckin
    6.07
     crap
    6.07
     goddamn
    6.00
     piss
    5.94
     bullshit
    5.92
    Activations Density 1.366%

    No Known Activations