© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 12405
    Prev
    Next
    INDEX
    Explanations

    the letter "W" as it pertains to names or references

    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
    1:0.05
    2:0.05
    3:0.07
    4:0.07
    5:0.06
    6:0.24
    7:0.05
    8:0.04
    9:0.21
    10:0.03
    11:0.04
    Negative Logits
     Abram
    -3.51
     Brist
    -3.45
     Osw
    -3.29
     Lind
    -3.22
     Higgins
    -3.13
     Bates
    -3.12
     Sham
    -2.95
     Winc
    -2.95
     Hod
    -2.90
     alias
    -2.90
    POSITIVE LOGITS
    Chip
    3.25
    chip
    3.18
    cars
    3.09
    wagen
    2.89
    borgh
    2.83
     Chip
    2.71
    processor
    2.68
    Autom
    2.67
    wana
    2.67
    aston
    2.64
    Activations Density 0.001%

    No Known Activations