© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9401
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Jeremy

    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
    0:0.05
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.18
    7:0.06
    8:0.05
    9:0.35
    10:0.02
    11:0.03
    Negative Logits
     Nas
    -3.63
     Cub
    -3.58
     Vi
    -3.49
    ��
    -3.48
    sson
    -3.45
    Cub
    -3.35
     condom
    -3.33
    anes
    -3.33
    appers
    -3.29
     Sod
    -3.24
    POSITIVE LOGITS
     Jeremy
    8.83
    Jeremy
    8.49
     Corbyn
    4.61
     Blair
    4.09
    byn
    3.97
     NK
    3.74
     Clarkson
    3.72
     Leon
    3.58
     Leigh
    3.54
     Bernie
    3.54
    Activations Density 0.002%

    No Known Activations