© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    alphanumeric combinations or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.31
    3:0.03
    4:0.06
    5:0.07
    6:0.02
    7:0.04
    8:0.28
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
    .''
    -2.80
    .」
    -2.74
    .�
    -2.65
     incorrectly
    -2.62
    ,''
    -2.62
     spirited
    -2.59
    �
    -2.56
    limits
    -2.51
     seeking
    -2.47
     ​
    -2.46
    POSITIVE LOGITS
    +
    6.95
    +,
    5.64
    +.
    5.37
    +)
    5.31
    -+
    4.64
    /+
    4.40
    YC
    4.30
    Ti
    4.03
    VB
    4.00
    PB
    3.99
    Activations Density 0.002%

    No Known Activations