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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13846
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or expressing frustration and being fed up with a situation

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.11
    1:0.02
    2:0.07
    3:0.12
    4:0.03
    5:0.06
    6:0.06
    7:0.04
    8:0.16
    9:0.17
    10:0.08
    11:0.04
    Negative Logits
     Normandy
    -1.28
    ��
    -1.27
    arget
    -1.20
     Amph
    -1.17
     geographic
    -1.15
     Towns
    -1.14
    framework
    -1.14
    JP
    -1.10
    quartered
    -1.10
    obook
    -1.09
    POSITIVE LOGITS
     indu
    1.29
     tip
    1.25
     swayed
    1.25
     intrig
    1.24
     blackmail
    1.24
     begs
    1.22
     bribe
    1.20
    ═
    1.17
    א
    1.16
    Shin
    1.16
    Activations Density 0.031%

    No Known Activations