© 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. 3-ATT-KK
    11. 7957
    Prev
    Next
    INDEX
    Explanations

    phrases indicating oppositions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.03
    2:0.09
    3:0.11
    4:0.02
    5:0.03
    6:0.05
    7:0.06
    8:0.10
    9:0.24
    10:0.08
    11:0.14
    Negative Logits
    ounding
    -1.32
    uctions
    -1.15
    ross
    -1.13
     downed
    -1.11
    OY
    -1.11
    eria
    -1.08
    ouple
    -1.05
     racked
    -1.05
    oké
    -1.03
    ornia
    -1.00
    POSITIVE LOGITS
    NetMessage
    1.24
    soDeliveryDate
    1.15
    ウス
    1.11
     prevailing
    1.11
    anism
    1.06
     oppos
    1.02
    soType
    1.01
    Champ
    1.00
     Lowell
    0.99
    Laughs
    0.98
    Activations Density 0.004%

    No Known Activations