© 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. 15032
    Prev
    Next
    INDEX
    Explanations

    references to sensitive or confidential information

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.28
    4:0.02
    5:0.15
    6:0.02
    7:0.04
    8:0.02
    9:0.02
    10:0.22
    11:0.02
    Negative Logits
    rompt
    -2.31
     urge
    -2.13
    uesday
    -2.11
    ellow
    -2.07
    nesday
    -2.04
    lus
    -2.04
     waving
    -1.98
    ilan
    -1.88
    rums
    -1.86
    okingly
    -1.85
    POSITIVE LOGITS
     archives
    2.98
     databases
    2.80
     journals
    2.47
     secrets
    2.42
     cached
    2.38
     intel
    2.35
     information
    2.30
     archive
    2.25
     resources
    2.24
     Archives
    2.21
    Activations Density 0.066%

    No Known Activations