© 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. 2-ATT-KK
    11. 21894
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to the dynamics of societal beliefs and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.05
    2:0.06
    3:0.08
    4:0.05
    5:0.15
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.15
    11:0.08
    Negative Logits
    SPONSORED
    -0.90
    eering
    -0.88
     targets
    -0.88
     wounding
    -0.87
     damaging
    -0.86
     downstream
    -0.84
     flowering
    -0.84
     unarmed
    -0.83
     inflicting
    -0.82
     Mount
    -0.82
    POSITIVE LOGITS
    maxwell
    1.49
     Answer
    1.43
    Answer
    1.31
    oiler
    1.16
    answered
    1.15
     guiActiveUn
    1.13
    answer
    1.09
    �
    1.06
     Idea
    1.05
     answer
    1.03
    Activations Density 0.076%

    No Known Activations