© 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. 20604
    Prev
    Next
    INDEX
    Explanations

    instances of laughter and emotional reactions

    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
    0:0.09
    1:0.03
    2:0.08
    3:0.13
    4:0.04
    5:0.07
    6:0.02
    7:0.07
    8:0.03
    9:0.02
    10:0.31
    11:0.04
    Negative Logits
     needing
    -2.67
     screaming
    -2.53
     NEED
    -2.52
     thirsty
    -2.50
     roaring
    -2.36
     hungry
    -2.31
    threatening
    -2.22
    need
    -2.20
     overflowing
    -2.18
     unbearable
    -2.18
    POSITIVE LOGITS
    inav
    2.23
    requent
    2.08
     minim
    2.03
     departures
    2.01
    orest
    1.99
     tolerated
    1.99
     longevity
    1.95
     minimize
    1.93
     exceptions
    1.93
    ettlement
    1.93
    Activations Density 0.001%

    No Known Activations