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. 9-ATT-KK
    6. 3171
    Prev
    Next
    INDEX
    Explanations

    entities related to collaborations and partnerships in various contexts, particularly in governance and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.01
    2:0.04
    3:0.18
    4:0.02
    5:0.06
    6:0.01
    7:0.05
    8:0.03
    9:0.02
    10:0.47
    11:0.02
    Negative Logits
    Wr
    -2.49
    WithNo
    -2.40
    ];
    -2.35
    retty
    -2.19
    ディ
    -2.15
     didnt
    -2.10
    ヘラ
    -2.07
    bia
    -2.06
    NULL
    -2.05
    )=
    -2.03
    POSITIVE LOGITS
    �
    2.23
     to
    2.17
     partners
    2.06
     stakeholders
    1.92
     toget
    1.90
     carefully
    1.82
     suppliers
    1.82
     interchange
    1.82
     converge
    1.82
     diligently
    1.80
    Activations Density 0.091%

    No Known Activations