© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 12341
    Prev
    Next
    INDEX
    Explanations

    links to web pages and computer programming terms related to setting up goals and funnels in Google Analytics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    elements related to links and resources in a digital context

    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
    1:0.08
    2:0.14
    3:0.13
    4:0.02
    5:0.07
    6:0.07
    7:0.06
    8:0.13
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
     Canaver
    -1.42
     Fiorina
    -1.24
    azeera
    -1.21
    athon
    -1.15
     Mellon
    -1.13
    ーティ
    -1.11
     Brisbane
    -1.10
    backer
    -1.09
     fundraiser
    -1.08
    HAEL
    -1.06
    POSITIVE LOGITS
    �
    1.22
     }}
    1.21
     subscribe
    1.14
    ></
    1.13
    tu
    1.08
    utm
    1.08
    }}
    1.07
    AppData
    1.06
     verb
    1.05
    ..."
    1.05
    Activations Density 0.007%

    No Known Activations