© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21838
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "at the forefront," indicating leadership or pioneering efforts in various contexts

    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
    1:0.03
    2:0.10
    3:0.06
    4:0.29
    5:0.06
    6:0.03
    7:0.02
    8:0.06
    9:0.18
    10:0.05
    11:0.03
    Negative Logits
    pload
    -1.64
    oshenko
    -1.54
     indiscrim
    -1.52
     unrelated
    -1.52
     surplus
    -1.46
    acet
    -1.41
     condol
    -1.36
     masse
    -1.36
     pods
    -1.31
     boarding
    -1.26
    POSITIVE LOGITS
     STATS
    1.50
    cipline
    1.45
    将
    1.45
     CLIENT
    1.31
     contender
    1.29
    ARGET
    1.28
    akra
    1.28
    是
    1.26
    三
    1.24
     BASE
    1.24
    Activations Density 0.003%

    No Known Activations