© 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. 16785
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to emotional expressions and audience reactions

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.28
    4:0.07
    5:0.06
    6:0.05
    7:0.05
    8:0.04
    9:0.03
    10:0.19
    11:0.05
    Negative Logits
    yrights
    -2.41
     immortality
    -2.29
    ogun
    -2.22
     precedent
    -2.20
     causation
    -2.16
     legality
    -2.14
     constitu
    -2.12
     warranty
    -2.11
    ="/
    -2.10
     rule
    -2.09
    POSITIVE LOGITS
     pauses
    2.63
    aughter
    2.24
     Removed
    2.19
     flashback
    2.18
    lightly
    2.17
     interrupted
    2.12
     fades
    2.11
    :]
    2.08
     gasped
    2.08
    interrupted
    2.02
    Activations Density 0.004%

    No Known Activations