© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22750
    Prev
    Next
    INDEX
    Explanations

    comparisons between different quantities or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that express increasing quantities or intensities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.10
    3:0.09
    4:0.33
    5:0.08
    6:0.02
    7:0.02
    8:0.03
    9:0.13
    10:0.06
    11:0.02
    Negative Logits
    ��
    -1.60
    yna
    -1.56
    aring
    -1.51
    ared
    -1.45
    ��
    -1.45
    xit
    -1.32
    uve
    -1.32
    aria
    -1.31
    Pic
    -1.31
    oped
    -1.31
    POSITIVE LOGITS
    udos
    1.54
     GOODMAN
    1.50
     misses
    1.49
     Revis
    1.36
     alike
    1.34
     surprises
    1.34
    brainer
    1.34
    INESS
    1.33
     BOX
    1.25
     bargain
    1.25
    Activations Density 0.035%

    No Known Activations