© 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. 20336
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships

    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
    0:0.23
    1:0.02
    2:0.16
    3:0.09
    4:0.03
    5:0.07
    6:0.03
    7:0.05
    8:0.18
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     Assy
    -2.81
    iHUD
    -2.79
    byn
    -2.76
     CET
    -2.68
     Instrument
    -2.65
    sov
    -2.64
     intervals
    -2.63
    isan
    -2.62
     Centauri
    -2.60
     Advent
    -2.60
    POSITIVE LOGITS
     Hogan
    6.76
     Hulk
    4.26
     Gawker
    3.57
     WWF
    3.47
     Wrestle
    3.47
     Playboy
    3.43
     wrestler
    3.42
     WWE
    3.35
     wrestling
    3.25
     TMZ
    3.02
    Activations Density 0.000%

    No Known Activations