© 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. 10-ATT-KK
    6. 15079
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or expressions of dissatisfaction

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.06
    4:0.06
    5:0.05
    6:0.03
    7:0.04
    8:0.02
    9:0.38
    10:0.04
    11:0.19
    Negative Logits
    xit
    -2.12
    ictional
    -2.09
    ocalyptic
    -2.01
    fake
    -1.98
     Gran
    -1.91
     Crack
    -1.91
    yth
    -1.87
     Theft
    -1.87
    icism
    -1.86
    hift
    -1.86
    POSITIVE LOGITS
    lished
    3.12
    stood
    2.93
     compensated
    2.88
     recognised
    2.86
     cared
    2.86
     thanked
    2.69
     respected
    2.66
     repaid
    2.65
     benefited
    2.62
     trained
    2.61
    Activations Density 0.012%

    No Known Activations