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. 10-ATT-KK
    6. 14741
    Prev
    Next
    INDEX
    Explanations

    keywords related to governmental and economic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.04
    2:0.05
    3:0.05
    4:0.09
    5:0.25
    6:0.03
    7:0.04
    8:0.04
    9:0.22
    10:0.04
    11:0.06
    Negative Logits
     except
    -3.46
     plus
    -3.24
     unless
    -3.16
     minus
    -3.11
     until
    -3.10
     either
    -3.08
     regardless
    -3.04
     including
    -2.97
    !
    -2.91
     combined
    -2.89
    POSITIVE LOGITS
    "))
    2.99
    ryu
    2.70
     ));
    2.65
    ));
    2.61
    BLIC
    2.49
    ���
    2.47
    Arg
    2.46
    ]);
    2.41
     ))
    2.35
    quickShipAvailable
    2.28
    Activations Density 0.003%

    No Known Activations