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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19418
    Prev
    Next
    INDEX
    Explanations

    indicators of significant events or situations that evoke emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.06
    3:0.15
    4:0.04
    5:0.04
    6:0.05
    7:0.02
    8:0.30
    9:0.08
    10:0.07
    11:0.05
    Negative Logits
     Klu
    -1.84
     Rasm
    -1.74
     Olson
    -1.70
     Ramsey
    -1.69
     Kaplan
    -1.64
     Beir
    -1.59
     Sched
    -1.59
     Sparks
    -1.58
     Jub
    -1.57
     Ramirez
    -1.57
    POSITIVE LOGITS
    addons
    2.16
    fort
    2.02
    wid
    1.97
    ui
    1.93
    )))
    1.92
    wiki
    1.92
    menu
    1.91
    ++)
    1.90
    ゴ
    1.89
    ゼウス
    1.84
    Activations Density 0.063%

    No Known Activations