Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating composition or ingredients of items or categories

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.22
    4:0.03
    5:0.05
    6:0.06
    7:0.17
    8:0.05
    9:0.05
    10:0.06
    11:0.16
    Negative Logits
    schild
    -1.46
    etsk
    -1.46
    Jr
    -1.43
    Jenn
    -1.32
    achi
    -1.31
    JR
    -1.29
    kiss
    -1.25
    rek
    -1.24
    gered
    -1.23
    claw
    -1.22
    POSITIVE LOGITS
     Guan
    1.49
     HDL
    1.30
     unspecified
    1.22
     Saiyan
    1.22
    �
    1.22
     phosphate
    1.21
    龍�
    1.21
     veins
    1.20
     varies
    1.18
     OD
    1.18
    Activations Density 0.002%

    No Known Activations