© 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. 12919
    Prev
    Next
    INDEX
    Explanations

    references to difficult personal experiences or struggles

    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
    0:0.14
    1:0.08
    2:0.20
    3:0.10
    4:0.05
    5:0.04
    6:0.05
    7:0.08
    8:0.06
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
    bestos
    -3.53
     Scorpion
    -3.36
     ACS
    -3.33
     Wichita
    -3.24
     asbestos
    -3.23
     Rhodes
    -3.19
     Methodist
    -3.12
     Tulsa
    -3.06
     Osc
    -2.94
     Hick
    -2.93
    POSITIVE LOGITS
    �
    5.08
    ノ
    4.80
    ヘ
    4.50
    �
    4.29
     �
    4.26
     �
    4.20
    テ
    4.18
    ─
    4.17
     �
    4.08
    ズ
    4.05
    Activations Density 0.031%

    No Known Activations