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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11286
    Prev
    Next
    INDEX
    Explanations

    phrases indicating skepticism or criticism, particularly regarding political figures or their actions

    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
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.22
    7:0.07
    8:0.09
    9:0.21
    10:0.02
    11:0.05
    Negative Logits
    DJ
    -4.42
    arius
    -4.04
     DJ
    -3.82
     Giov
    -3.72
     Dynamo
    -3.71
    lux
    -3.57
    roit
    -3.46
     techno
    -3.39
     Mechanical
    -3.30
    sterdam
    -3.27
    POSITIVE LOGITS
     Palin
    11.41
     Sarah
    5.72
    Pal
    5.49
    Sarah
    5.08
     Alaska
    4.96
     Limbaugh
    4.65
     Anchorage
    4.62
     Pal
    4.49
     McCain
    4.46
     Helena
    4.21
    Activations Density 0.007%

    No Known Activations