© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23017
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning, decision-making, and urgency

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

    phrases related to urgency or quick actions

    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
    0:0.05
    1:0.02
    2:0.19
    3:0.05
    4:0.25
    5:0.05
    6:0.02
    7:0.03
    8:0.08
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
     Sins
    -1.73
    jiang
    -1.62
     Qiao
    -1.55
    ��
    -1.51
    将
    -1.48
    DN
    -1.43
    フォ
    -1.43
    �
    -1.42
    NAS
    -1.41
     yourselves
    -1.39
    POSITIVE LOGITS
     curtains
    1.68
     cones
    1.50
    oscopic
    1.45
     curtain
    1.43
     madness
    1.42
     conformity
    1.34
     insanity
    1.34
    ready
    1.33
    monary
    1.31
     vomit
    1.28
    Activations Density 0.005%

    No Known Activations