© 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. 2-ATT-KK
    11. 13439
    Prev
    Next
    INDEX
    Explanations

    information or details related to the design or creation process

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.01
    2:0.08
    3:0.06
    4:0.04
    5:0.17
    6:0.02
    7:0.10
    8:0.04
    9:0.07
    10:0.18
    11:0.10
    Negative Logits
     Leaders
    -0.92
     Bills
    -0.87
    oğ
    -0.87
     Pigs
    -0.84
     Bom
    -0.83
     Cambod
    -0.83
     Hawks
    -0.83
     Rabb
    -0.81
     Donovan
    -0.80
     Hos
    -0.80
    POSITIVE LOGITS
    ディ
    1.17
    ツ
    1.16
    イト
    0.97
    ワン
    0.93
    ュ
    0.93
    00200000
    0.90
    ット
    0.89
    版
    0.88
    =#
    0.85
    ドラ
    0.85
    Activations Density 1.216%

    No Known Activations