Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11412
    Prev
    Next
    INDEX
    Explanations

    references to control and dominance in relationships or interactions

    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
    0:0.08
    1:0.01
    2:0.05
    3:0.21
    4:0.02
    5:0.14
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.32
    11:0.01
    Negative Logits
    apor
    -2.14
     Alone
    -2.09
     entirely
    -1.99
     altogether
    -1.98
    =(
    -1.97
    Rum
    -1.93
    YR
    -1.90
    emale
    -1.87
    ranch
    -1.86
    Synopsis
    -1.85
    POSITIVE LOGITS
     willingness
    2.63
     readiness
    2.53
     chops
    2.46
     sophistication
    2.40
     depth
    2.27
     versatility
    2.21
     richness
    2.14
     patience
    2.14
     kindness
    2.06
     prowess
    2.05
    Activations Density 0.124%

    No Known Activations