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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10691
    Prev
    Next
    INDEX
    Explanations

    references to significant political events and figures, particularly related to corruption and governmental actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.05
    4:0.07
    5:0.02
    6:0.26
    7:0.06
    8:0.07
    9:0.24
    10:0.02
    11:0.03
    Negative Logits
     ox
    -3.73
     hyd
    -3.64
     ELE
    -3.60
     brid
    -3.52
     moisture
    -3.47
    rain
    -3.45
     Water
    -3.44
     corro
    -3.34
     ASIC
    -3.31
     resil
    -3.25
    POSITIVE LOGITS
     Kennedy
    10.59
    Kenn
    9.67
     JFK
    7.95
     Castro
    6.07
    FK
    5.83
     Kenn
    5.64
    Roberts
    5.03
     Roberts
    4.74
     Oswald
    4.74
     1963
    4.70
    Activations Density 0.013%

    No Known Activations