© 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. 7330
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to leadership and authority

    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
    1:0.01
    2:0.10
    3:0.08
    4:0.08
    5:0.32
    6:0.02
    7:0.03
    8:0.02
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
    ?),
    -3.55
    !),
    -3.04
    ?)
    -2.60
    theless
    -2.49
    ingly
    -2.48
     whiff
    -2.46
     definitely
    -2.40
     blatantly
    -2.31
    ?]
    -2.31
     humiliating
    -2.28
    POSITIVE LOGITS
    .�
    4.61
    �
    3.87
    .''.
    3.66
    ."
    3.58
    .</
    3.50
    .''
    3.43
    .*
    3.34
    ''.
    3.29
    _.
    3.25
    ".
    3.17
    Activations Density 0.131%

    No Known Activations