© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21627
    Prev
    Next
    INDEX
    Explanations

    negative contractions related to denial or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.04
    2:0.08
    3:0.06
    4:0.15
    5:0.09
    6:0.03
    7:0.12
    8:0.03
    9:0.09
    10:0.07
    11:0.04
    Negative Logits
     Somers
    -3.06
     Wilmington
    -2.99
     incorpor
    -2.93
     Newark
    -2.91
     cigars
    -2.88
     cigar
    -2.87
     Uk
    -2.81
     nic
    -2.78
    worms
    -2.74
     Veronica
    -2.73
    POSITIVE LOGITS
    �
    5.11
    †
    4.32
    �
    4.24
    ‎
    4.08
    ▓
    4.04
    ​​
    4.04
     �
    3.78
    ヘ
    3.73
     │
    3.71
    】
    3.69
    Activations Density 0.065%

    No Known Activations