© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22702
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and research institutes

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

    references to various entities, particularly those related to scientific, medical, or technical subjects, as well as actions associated with them

    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
    0:0.11
    1:0.02
    2:0.04
    3:0.13
    4:0.03
    5:0.13
    6:0.05
    7:0.07
    8:0.12
    9:0.05
    10:0.14
    11:0.07
    Negative Logits
    ��
    -1.21
    eanor
    -1.07
    etheless
    -1.05
    ulhu
    -1.05
     nomine
    -1.04
    galitarian
    -1.04
    swer
    -1.03
    emonium
    -1.03
    ongyang
    -1.02
    olulu
    -1.01
    POSITIVE LOGITS
    Wave
    1.08
    BuyableInstoreAndOnline
    0.95
    Tra
    0.94
    osc
    0.94
     runners
    0.93
    BB
    0.91
    Boss
    0.91
    Favorite
    0.91
    rav
    0.88
    uca
    0.86
    Activations Density 0.111%

    No Known Activations