© 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. 20906
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and variations related to it

    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
    0:0.15
    1:0.03
    2:0.06
    3:0.05
    4:0.06
    5:0.06
    6:0.10
    7:0.02
    8:0.03
    9:0.33
    10:0.02
    11:0.03
    Negative Logits
     Jenner
    -3.81
     GoPro
    -3.33
     Disco
    -3.28
    icho
    -3.25
     TM
    -3.23
     Dash
    -3.21
     McKenna
    -3.10
    TM
    -3.09
     pav
    -3.08
     Davidson
    -3.08
    POSITIVE LOGITS
    letter
    7.84
     letter
    7.78
    Letter
    7.21
     Letter
    7.05
     letters
    7.01
    letters
    6.99
     Letters
    6.28
     LET
    5.31
     correspondence
    4.47
     mail
    3.92
    Activations Density 0.016%

    No Known Activations