© 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. 3-ATT-KK
    11. 10582
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.11
    2:0.08
    3:0.05
    4:0.02
    5:0.06
    6:0.08
    7:0.09
    8:0.15
    9:0.08
    10:0.12
    11:0.07
    Negative Logits
     srf
    -1.09
    ÃÂ
    -0.95
     tradem
    -0.90
     colonies
    -0.86
     pione
    -0.85
     births
    -0.84
     majors
    -0.84
     theor
    -0.84
    uberty
    -0.83
    aeper
    -0.82
    POSITIVE LOGITS
     "@
    1.20
    Offline
    1.11
     "#
    1.08
    ESA
    1.06
    ory
    1.01
    "))
    0.99
    orage
    0.99
    Nik
    0.97
    seless
    0.96
    Snow
    0.95
    Activations Density 0.045%

    No Known Activations