© 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. 14691
    Prev
    Next
    INDEX
    Explanations

    exaggerated descriptions and dynamic 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
    0:0.04
    1:0.01
    2:0.03
    3:0.13
    4:0.11
    5:0.05
    6:0.05
    7:0.05
    8:0.33
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
     Holden
    -3.90
    Carter
    -3.79
     Elon
    -3.72
     Goldberg
    -3.44
     Richards
    -3.44
     Carter
    -3.34
     Whale
    -3.29
     Rockets
    -3.27
     Bezos
    -3.23
     Hawks
    -3.15
    POSITIVE LOGITS
    �
    7.48
     �
    7.11
     �
    7.02
    �
    6.27
    �
    6.09
     Romanian
    4.90
    ć
    4.63
    ł
    4.59
     Sloven
    4.23
    ş
    4.21
    Activations Density 0.043%

    No Known Activations