© 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. 9-ATT-KK
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    issues related to social attitudes and behaviors involving privilege and gender identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.02
    2:0.07
    3:0.37
    4:0.04
    5:0.13
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.12
    11:0.02
    Negative Logits
    ================================================================
    -2.15
    }}}
    -2.05
     comrade
    -2.04
    nsics
    -2.04
    Doc
    -2.03
    Acknowled
    -2.02
    !!!!!!!!
    -1.99
    !!!!!
    -1.99
    _.
    -1.96
    stros
    -1.95
    POSITIVE LOGITS
     respondents
    2.88
     disproportionately
    2.88
     decreased
    2.81
     tended
    2.74
     disliked
    2.55
     favored
    2.54
     favoured
    2.54
     perceived
    2.53
     accounted
    2.52
     correlated
    2.50
    Activations Density 0.405%

    No Known Activations