© 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. 17307
    Prev
    Next
    INDEX
    Explanations

    references to political entities and the consequences of their actions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.03
    3:0.03
    4:0.04
    5:0.11
    6:0.02
    7:0.04
    8:0.02
    9:0.43
    10:0.02
    11:0.14
    Negative Logits
    quartered
    -2.25
    icipated
    -2.07
     compan
    -2.06
    arers
    -2.03
    fitting
    -1.97
     collaborating
    -1.96
     coordinating
    -1.92
    ertodd
    -1.92
    enegger
    -1.91
    having
    -1.91
    POSITIVE LOGITS
     into
    3.54
    into
    3.21
     against
    2.94
     Into
    2.79
     INTO
    2.78
     toward
    2.58
     towards
    2.44
     away
    2.35
    brow
    2.35
     onto
    2.33
    Activations Density 0.131%

    No Known Activations