© 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. 247
    Prev
    Next
    INDEX
    Explanations

    negative symbols and phrases indicating disapproval or rejection

    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
    0:0.04
    1:0.31
    2:0.03
    3:0.18
    4:0.04
    5:0.08
    6:0.05
    7:0.05
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    UGE
    -2.50
    entimes
    -2.48
     earthqu
    -2.32
     skewed
    -2.14
     mistaken
    -2.11
    OOL
    -2.11
     indistinguishable
    -2.07
     taller
    -2.06
    inged
    -2.06
     longer
    -2.05
    POSITIVE LOGITS
    shall
    3.50
    23
    2.84
    bye
    2.73
    ratulations
    2.72
    iae
    2.70
    conduct
    2.68
    22
    2.66
    25
    2.55
    28
    2.51
    hew
    2.46
    Activations Density 0.001%

    No Known Activations