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. 14642
    Prev
    Next
    INDEX
    Explanations

    contact information, particularly emails and social media handles

    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
    0:0.09
    1:0.02
    2:0.02
    3:0.06
    4:0.23
    5:0.04
    6:0.11
    7:0.06
    8:0.12
    9:0.05
    10:0.11
    11:0.02
    Negative Logits
    !'
    -2.64
    ');
    -2.60
    ';
    -2.52
    ',"
    -2.42
    stocks
    -2.40
    ,'
    -2.38
    '>
    -2.38
     OPEC
    -2.38
     Kag
    -2.36
     Belgian
    -2.35
    POSITIVE LOGITS
     Chronicle
    3.15
     annotations
    2.66
    ��
    2.63
    word
    2.49
    Listener
    2.47
    Correction
    2.34
    phabet
    2.33
     Compton
    2.32
     citation
    2.30
    sf
    2.28
    Activations Density 0.002%

    No Known Activations