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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8979
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events related to Brexit negotiations

    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
    0:0.08
    1:0.05
    2:0.00
    3:0.11
    4:0.13
    5:0.12
    6:0.09
    7:0.04
    8:0.16
    9:0.12
    10:0.02
    11:0.03
    Negative Logits
    ologne
    -1.81
     Azerb
    -1.78
    orks
    -1.77
    etts
    -1.76
    itures
    -1.75
    gars
    -1.73
    [/
    -1.73
    erie
    -1.67
    tons
    -1.65
    enhagen
    -1.60
    POSITIVE LOGITS
     Rupert
    1.79
    ribly
    1.75
     sprayed
    1.70
     Pelosi
    1.68
    Jeff
    1.66
    Container
    1.66
    WARN
    1.63
    INE
    1.59
     dismantle
    1.58
    Fight
    1.55
    Activations Density 0.003%

    No Known Activations