© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 15795
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting or opposing elements

    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
    0:0.04
    1:0.02
    2:0.13
    3:0.08
    4:0.04
    5:0.14
    6:0.03
    7:0.07
    8:0.09
    9:0.08
    10:0.15
    11:0.07
    Negative Logits
    istries
    -1.16
    estyles
    -1.15
    habi
    -0.94
    plete
    -0.93
    ouf
    -0.93
    uds
    -0.90
    acs
    -0.88
     abl
    -0.88
     Flames
    -0.88
    alions
    -0.87
    POSITIVE LOGITS
    "))
    0.93
    quickShipAvailable
    0.93
    Bey
    0.91
    nob
    0.90
    ritical
    0.82
    ���
    0.81
     Sunder
    0.80
     Assignment
    0.79
     Ley
    0.79
     }}
    0.77
    Activations Density 0.225%

    No Known Activations