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

    Neuronpedia

    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. 10898
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "by"

    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
    0:0.04
    1:0.05
    2:0.05
    3:0.16
    4:0.03
    5:0.04
    6:0.12
    7:0.05
    8:0.13
    9:0.07
    10:0.14
    11:0.06
    Negative Logits
    Downloadha
    -1.10
    istan
    -1.08
     Geek
    -1.03
    Disclaimer
    -1.03
    abad
    -1.01
    Bey
    -0.99
     DevOnline
    -0.95
    wegian
    -0.94
    gy
    -0.92
    Born
    -0.91
    POSITIVE LOGITS
    etheless
    1.42
    \">
    1.25
    theless
    1.22
    quished
    1.11
     Gou
    1.09
    alon
    1.04
    erity
    1.04
    kefeller
    0.97
    usterity
    0.94
    mares
    0.92
    Activations Density 0.153%

    No Known Activations