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. 9550
    Prev
    Next
    INDEX
    Explanations

    references to individuals related to Trump and his family

    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
    0:0.12
    1:0.06
    2:0.01
    3:0.13
    4:0.06
    5:0.12
    6:0.06
    7:0.03
    8:0.24
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
     Explos
    -1.89
     psi
    -1.72
     probabilities
    -1.71
     shootout
    -1.68
     explosives
    -1.66
     Lethal
    -1.65
     toxin
    -1.62
     noise
    -1.59
     ammonia
    -1.57
     trap
    -1.56
    POSITIVE LOGITS
     Ivanka
    2.38
     Melania
    2.02
     Kardashian
    1.96
    Disney
    1.84
    branded
    1.80
    abee
    1.76
     apparel
    1.72
     departing
    1.69
     debuted
    1.67
     Instagram
    1.66
    Activations Density 0.005%

    No Known Activations