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. 3-ATT-KK
    6. 10426
    Prev
    Next
    INDEX
    Explanations

    phrases related to question-and-answer formats and forums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.35
    4:0.01
    5:0.02
    6:0.09
    7:0.18
    8:0.05
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    ゼウス
    -1.64
    hyde
    -1.36
    wake
    -1.27
    flu
    -1.21
    stead
    -1.20
    �
    -1.15
    ール
    -1.15
    SourceFile
    -1.14
    panic
    -1.14
    apeake
    -1.12
    POSITIVE LOGITS
     elig
    1.46
     jurisdiction
    1.20
     colleg
    1.18
     particulars
    1.11
    zai
    1.09
     Directions
    1.09
    �醒
    1.07
     Authority
    1.06
    odox
    1.06
     why
    1.06
    Activations Density 0.029%

    No Known Activations