© 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. 9-ATT-KK
    11. 4948
    Prev
    Next
    INDEX
    Explanations

    mentions of ratings or evaluations related to media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.11
    4:0.04
    5:0.05
    6:0.04
    7:0.05
    8:0.43
    9:0.03
    10:0.03
    11:0.04
    Negative Logits
    imaru
    -3.72
    ryu
    -3.01
     Bleach
    -2.82
     Feng
    -2.72
    agara
    -2.67
     Rouge
    -2.65
    Nar
    -2.65
    adh
    -2.64
    amaru
    -2.61
     Hait
    -2.60
    POSITIVE LOGITS
     Juda
    3.87
     Jewish
    3.69
     rabbi
    3.65
    Jewish
    3.55
     Torah
    3.51
     Hebrew
    3.41
     Rabbi
    3.41
    Israel
    3.34
     Jews
    3.33
     Judaism
    3.31
    Activations Density 0.001%

    No Known Activations