© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11859
    Prev
    Next
    INDEX
    Explanations

    automobile model numbers

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

    Roman numerals and sequences of numbers

    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
    0:0.05
    1:0.04
    2:0.08
    3:0.24
    4:0.04
    5:0.03
    6:0.11
    7:0.09
    8:0.04
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    PDATE
    -1.37
    steen
    -1.20
    querque
    -1.16
    enhagen
    -1.14
     behavi
    -1.13
    olkien
    -1.11
     weaken
    -1.11
    eworks
    -1.09
    ranging
    -1.06
     ado
    -1.06
    POSITIVE LOGITS
    龍喚士
    1.17
     Shang
    1.17
    360
    1.12
     Pry
    1.09
    470
    1.03
    ibu
    1.02
    ��
    1.01
    elta
    0.99
    tiny
    0.98
    �
    0.97
    Activations Density 0.002%

    No Known Activations