© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 8752
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional reactions or expressions

    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
    0:0.05
    1:0.03
    2:0.04
    3:0.05
    4:0.05
    5:0.03
    6:0.22
    7:0.06
    8:0.06
    9:0.30
    10:0.02
    11:0.04
    Negative Logits
    Lev
    -4.01
     Peck
    -3.62
    ş
    -3.53
    zbollah
    -3.40
    ike
    -3.38
    iked
    -3.26
     Barker
    -3.22
    zl
    -3.21
     Jensen
    -3.20
     Nest
    -3.18
    POSITIVE LOGITS
    George
    8.72
     George
    8.32
     Georg
    6.23
    Georg
    5.69
    ORGE
    5.19
    Georgia
    4.55
     Sanford
    4.19
    GA
    4.12
     GW
    4.10
     Trayvon
    4.04
    Activations Density 0.010%

    No Known Activations