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. 7725
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an increase or repetition in quantity or degree

    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
    0:0.07
    1:0.05
    2:0.08
    3:0.06
    4:0.02
    5:0.09
    6:0.12
    7:0.07
    8:0.05
    9:0.04
    10:0.14
    11:0.15
    Negative Logits
    ��
    -1.16
     Bastard
    -1.10
     Shack
    -1.05
     Interpret
    -1.05
    ↵ 
    -1.01
    audi
    -1.00
     beacon
    -1.00
     haunt
    -0.98
    NK
    -0.94
     narrator
    -0.94
    POSITIVE LOGITS
     than
    1.29
    than
    1.26
    ahime
    1.19
    ��
    1.13
    RESULTS
    1.10
    cellaneous
    1.04
    ravings
    1.02
    consuming
    1.02
     repay
    1.02
    quickShipAvailable
    1.01
    Activations Density 0.118%

    No Known Activations