© 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. 5-ATT-KK
    6. 28973
    Prev
    Next
    INDEX
    Explanations

    the word "don't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.08
    4:0.10
    5:0.06
    6:0.08
    7:0.09
    8:0.06
    9:0.07
    10:0.07
    11:0.08
    Negative Logits
     Scar
    -2.00
     Collider
    -1.82
     Tears
    -1.81
     Events
    -1.76
     Pony
    -1.71
     Variety
    -1.66
     Legions
    -1.60
     Huck
    -1.59
     Hawking
    -1.57
     Rock
    -1.57
    POSITIVE LOGITS
    arent
    1.92
    ğ
    1.76
    mort
    1.67
     compan
    1.65
     awa
    1.64
     <[
    1.63
    utherland
    1.62
    penter
    1.62
    sole
    1.60
    gaard
    1.59
    Activations Density 0.000%

    No Known Activations