© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28312
    Prev
    Next
    INDEX
    Explanations

    negations and qualifiers related to capabilities or changes

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.13
    4:0.06
    5:0.06
    6:0.21
    7:0.03
    8:0.06
    9:0.10
    10:0.12
    11:0.05
    Negative Logits
    ials
    -1.15
    ADVERTISEMENT
    -1.12
    iling
    -1.12
     dile
    -1.05
     supportive
    -1.03
    hips
    -1.02
    bie
    -1.01
     fare
    -1.00
     retiring
    -1.00
     achie
    -1.00
    POSITIVE LOGITS
    フォ
    1.56
    ヴァ
    1.43
    purpose
    1.29
    DragonMagazine
    1.28
    oya
    1.27
    emonium
    1.24
    ゼ
    1.24
    sth
    1.21
    ヤ
    1.20
    widget
    1.17
    Activations Density 0.173%

    No Known Activations