© 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. 13534
    Prev
    Next
    INDEX
    Explanations

    references to notable quotes or statements made by individuals

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.28
    7:0.04
    8:0.09
    9:0.24
    10:0.01
    11:0.03
    Negative Logits
     Parm
    -4.11
     ammon
    -4.00
     Seym
    -3.91
     mattress
    -3.61
     Nept
    -3.46
    aukee
    -3.44
     pivot
    -3.40
     subscript
    -3.38
     Brut
    -3.26
    ript
    -3.25
    POSITIVE LOGITS
    Lee
    11.30
     Lee
    10.67
    lee
    5.17
     Choi
    5.16
     Wong
    4.94
     Huang
    4.49
     Seoul
    4.45
     Lewis
    4.35
    Lewis
    4.19
     Korea
    4.18
    Activations Density 0.017%

    No Known Activations