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. 7-ATT-KK
    6. 9528
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opportunities or favorable moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.25
    1:0.02
    2:0.01
    3:0.10
    4:0.06
    5:0.03
    6:0.03
    7:0.02
    8:0.34
    9:0.08
    10:0.01
    11:0.01
    Negative Logits
     leveled
    -1.99
    ドラ
    -1.84
    fired
    -1.81
    rons
    -1.79
    noxious
    -1.78
    grow
    -1.78
    icated
    -1.76
    reviewed
    -1.75
    received
    -1.71
    semble
    -1.68
    POSITIVE LOGITS
     opportunity
    2.24
     Caption
    1.85
     Anniversary
    1.84
    Reward
    1.82
     mating
    1.80
     excuse
    1.78
    "}],"
    1.75
     anniversary
    1.75
     temptation
    1.66
     eternity
    1.64
    Activations Density 0.003%

    No Known Activations