© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12194
    Prev
    Next
    INDEX
    Explanations

    references to influential figures and their actions in socio-political contexts

    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
    1:0.26
    2:0.06
    3:0.07
    4:0.04
    5:0.02
    6:0.10
    7:0.14
    8:0.02
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
    regor
    -2.71
    estern
    -2.53
    ront
    -2.48
    orks
    -2.43
    GER
    -2.25
    MpServer
    -2.25
    Hung
    -2.23
    rican
    -2.17
    esses
    -2.17
     medium
    -2.14
    POSITIVE LOGITS
     White
    5.59
    White
    4.67
     Black
    3.93
     WHITE
    3.36
     Whites
    3.34
    Black
    3.16
     Blue
    3.13
     Red
    2.97
     0004
    2.85
     Archdemon
    2.79
    Activations Density 0.008%

    No Known Activations