© 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. 2-ATT-KK
    11. 22185
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertisements or viewer engagement

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.12
    1:0.05
    2:0.07
    3:0.08
    4:0.05
    5:0.11
    6:0.08
    7:0.03
    8:0.09
    9:0.12
    10:0.10
    11:0.05
    Negative Logits
    rower
    -1.46
     mechanically
    -1.20
     finally
    -1.20
     neglig
    -1.20
     contracted
    -1.13
     contracting
    -1.12
     settled
    -1.12
     fortunate
    -1.11
     hereby
    -1.08
     gene
    -1.07
    POSITIVE LOGITS
    adders
    1.47
     rooft
    1.31
    interstitial
    1.28
    Iv
    1.27
     VIDEOS
    1.22
     裏�
    1.20
    cuts
    1.18
    smart
    1.17
    SPONSORED
    1.16
    �
    1.16
    Activations Density 0.002%

    No Known Activations