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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18966
    Prev
    Next
    INDEX
    Explanations

    descriptions of opulent or lavish settings

    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
    0:0.07
    1:0.06
    2:0.05
    3:0.10
    4:0.06
    5:0.16
    6:0.08
    7:0.06
    8:0.09
    9:0.14
    10:0.03
    11:0.04
    Negative Logits
    amaz
    -2.31
    $$$$
    -2.08
    ennes
    -2.05
     Dickens
    -1.97
    aughs
    -1.90
    elong
    -1.89
     Pasadena
    -1.85
     Hannity
    -1.84
    illy
    -1.84
    gettable
    -1.81
    POSITIVE LOGITS
     Sovere
    1.97
    anium
    1.97
     cloning
    1.96
    CLASSIFIED
    1.93
     patents
    1.92
     pending
    1.80
     hinges
    1.79
     implants
    1.77
    Its
    1.76
     titanium
    1.74
    Activations Density 0.000%

    No Known Activations