© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9562
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize repetition or similarity

    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
    1:0.03
    2:0.02
    3:0.28
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.09
    9:0.03
    10:0.27
    11:0.03
    Negative Logits
    姫
    -2.09
     unlawfully
    -1.97
     oppressed
    -1.84
     dictators
    -1.83
     prematurely
    -1.81
     violently
    -1.81
     illegally
    -1.79
    raised
    -1.76
     abused
    -1.76
     enemy
    -1.74
    POSITIVE LOGITS
     inception
    2.39
     moment
    2.35
    cember
    2.34
     culmination
    2.34
     outset
    2.24
     beginnings
    2.19
    nesday
    2.16
    ruary
    2.15
     pinnacle
    2.11
    levard
    2.11
    Activations Density 0.086%

    No Known Activations