© 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. 21837
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships and connections, particularly in the context of actions or relationships between entities

    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
    0:0.04
    1:0.02
    2:0.11
    3:0.04
    4:0.38
    5:0.05
    6:0.03
    7:0.03
    8:0.13
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
    hao
    -1.56
    qual
    -1.50
    ucket
    -1.42
    bringer
    -1.37
    ran
    -1.31
    forms
    -1.30
    etsk
    -1.30
    aka
    -1.29
    ��
    -1.28
    than
    -1.26
    POSITIVE LOGITS
    channelAvailability
    1.37
     Etsy
    1.36
     psychiat
    1.31
     adultery
    1.31
    ALSE
    1.30
     resume
    1.30
     acquaintances
    1.27
    adesh
    1.27
    lished
    1.27
     greeting
    1.26
    Activations Density 0.011%

    No Known Activations