© 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. 5-ATT-KK
    11. 17137
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.07
    2:0.08
    3:0.09
    4:0.08
    5:0.07
    6:0.05
    7:0.09
    8:0.09
    9:0.09
    10:0.09
    11:0.09
    Negative Logits
     Jewish
    -1.57
     nuts
    -1.54
     HRC
    -1.53
    6666
    -1.44
    rity
    -1.43
    hire
    -1.42
     boycot
    -1.42
     educated
    -1.42
     Gujar
    -1.41
    bie
    -1.41
    POSITIVE LOGITS
    apter
    1.64
    rys
    1.63
     Decay
    1.62
    doms
    1.60
     teasp
    1.51
    xtap
    1.46
    ynt
    1.46
     eleph
    1.45
    ipel
    1.41
     Deadly
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.