© 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. 9-ATT-KK
    11. 3263
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggle and personal challenges

    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
    0:0.06
    1:0.02
    2:0.10
    3:0.39
    4:0.03
    5:0.13
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.07
    11:0.01
    Negative Logits
     precedent
    -2.20
     likeness
    -2.02
     plurality
    -2.00
    者
    -2.00
     distinction
    -1.86
    oliath
    -1.83
    oppable
    -1.83
     legitimacy
    -1.83
    ieft
    -1.83
     implication
    -1.81
    POSITIVE LOGITS
     lunch
    3.14
     breakfast
    3.12
     dinner
    3.06
     chores
    2.94
     brunch
    2.94
     snacks
    2.87
     dinners
    2.82
     weekends
    2.72
     supper
    2.70
     meals
    2.69
    Activations Density 1.700%

    No Known Activations