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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22466
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, specifically names of people and places

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

    references to specific individuals or entities in the context of sports or events

    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
    0:0.07
    1:0.04
    2:0.26
    3:0.08
    4:0.09
    5:0.11
    6:0.03
    7:0.03
    8:0.03
    9:0.13
    10:0.05
    11:0.04
    Negative Logits
    owship
    -1.39
     unfocusedRange
    -1.34
    ��
    -1.34
    MpServer
    -1.30
    ��
    -1.28
    IONS
    -1.27
    YING
    -1.26
    ��
    -1.21
    QL
    -1.20
    INGTON
    -1.19
    POSITIVE LOGITS
    kh
    1.36
    igham
    1.15
    igans
    1.15
    legraph
    1.14
    raz
    1.12
    aminer
    1.10
    opol
    1.10
     Bor
    1.09
    illin
    1.07
    fters
    1.07
    Activations Density 0.000%

    No Known Activations