© 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. 16339
    Prev
    Next
    INDEX
    Explanations

    references to specific events, roles, and actions in a political or institutional context

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.03
    4:0.04
    5:0.20
    6:0.02
    7:0.02
    8:0.02
    9:0.44
    10:0.02
    11:0.04
    Negative Logits
    aughs
    -2.48
     Their
    -2.39
    Their
    -2.37
    .'
    -2.29
    .?
    -2.28
    .
    -2.22
    .]
    -2.15
     They
    -2.14
    They
    -2.07
    +.
    -2.06
    POSITIVE LOGITS
     between
    2.13
     against
    2.08
     atop
    2.00
     midway
    1.83
    �
    1.82
    �
    1.80
    ェ
    1.72
     toward
    1.71
    ��
    1.70
     towards
    1.64
    Activations Density 0.708%

    No Known Activations