© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12754
    Prev
    Next
    INDEX
    Explanations

    the presence of significant or iconic objects, particularly golden idols

    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
    0:0.11
    1:0.03
    2:0.09
    3:0.05
    4:0.03
    5:0.06
    6:0.15
    7:0.05
    8:0.13
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
     Cambridge
    -3.91
    guyen
    -3.75
    wine
    -3.75
    glas
    -3.55
    renheit
    -3.55
     CoC
    -3.49
     Vermont
    -3.46
     Thornton
    -3.44
     Welch
    -3.33
    oultry
    -3.33
    POSITIVE LOGITS
     idol
    9.68
     idols
    9.00
     Idol
    8.66
     Baal
    6.15
    ㅋㅋ
    3.94
     Eden
    3.90
     Jung
    3.88
     Yug
    3.65
     Bieber
    3.63
     Pharaoh
    3.58
    Activations Density 0.001%

    No Known Activations