© 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. 15294
    Prev
    Next
    INDEX
    Explanations

    temporal indicators and sequences related to events or actions

    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
    1:0.03
    2:0.06
    3:0.30
    4:0.05
    5:0.15
    6:0.03
    7:0.07
    8:0.04
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     billions
    -2.13
     entitle
    -1.97
     entitlement
    -1.82
     disrupting
    -1.78
     costing
    -1.77
     trillions
    -1.70
     millions
    -1.66
     dwarf
    -1.66
     suffering
    -1.65
     blacklist
    -1.64
    POSITIVE LOGITS
    byss
    1.85
     Edited
    1.84
    romptu
    1.81
    illation
    1.79
     Ibid
    1.77
    cerpt
    1.76
    ée
    1.74
    iece
    1.72
     Bened
    1.69
    cture
    1.69
    Activations Density 0.049%

    No Known Activations