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. 3-ATT-KK
    6. 10759
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to flexibility and adaptability in various contexts

    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
    0:0.02
    1:0.02
    2:0.06
    3:0.15
    4:0.02
    5:0.04
    6:0.06
    7:0.18
    8:0.05
    9:0.06
    10:0.07
    11:0.19
    Negative Logits
    usra
    -1.36
    roy
    -1.22
    士
    -1.21
     Deaths
    -1.21
    rolet
    -1.20
     Trayvon
    -1.18
     Corruption
    -1.16
    death
    -1.16
    urga
    -1.15
    pain
    -1.13
    POSITIVE LOGITS
     accommodating
    1.39
    cipl
    1.31
     agile
    1.27
    cipled
    1.26
     accommod
    1.24
     athlet
    1.24
     responsiveness
    1.23
     srfAttach
    1.21
    Course
    1.21
     stances
    1.19
    Activations Density 0.012%

    No Known Activations