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. 10178
    Prev
    Next
    INDEX
    Explanations

    repeated phrases that emphasize or draw attention to specific subjects or topics

    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
    0:0.09
    1:0.05
    2:0.14
    3:0.03
    4:0.04
    5:0.07
    6:0.15
    7:0.06
    8:0.05
    9:0.04
    10:0.17
    11:0.06
    Negative Logits
    ���
    -1.09
    ��
    -1.06
     Roof
    -1.01
     DDR
    -0.99
     Ake
    -0.96
    ��
    -0.95
     Photograph
    -0.95
     Fif
    -0.92
    864
    -0.90
     Amin
    -0.90
    POSITIVE LOGITS
     porous
    1.13
    Privacy
    1.11
    wikipedia
    1.11
    emouth
    1.07
     respective
    1.06
     helicop
    1.01
    assic
    1.01
    Especially
    0.99
    orget
    0.99
    bilt
    0.99
    Activations Density 0.113%

    No Known Activations