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. 3062
    Prev
    Next
    INDEX
    Explanations

    references to the Boko Haram group and its activities

    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
    0:0.06
    1:0.01
    2:0.05
    3:0.08
    4:0.02
    5:0.05
    6:0.07
    7:0.04
    8:0.43
    9:0.08
    10:0.03
    11:0.02
    Negative Logits
     Bohem
    -3.68
    chwitz
    -3.63
     Rosenthal
    -3.62
     Austrian
    -3.42
     Stanton
    -3.37
     Poles
    -3.34
     Polish
    -3.32
     Austria
    -3.27
     Schwar
    -3.22
     Schmidt
    -3.19
    POSITIVE LOGITS
     Boko
    8.73
     Nigeria
    8.31
     Nigerian
    8.11
     Niger
    7.07
     Cameroon
    6.61
     Rodrig
    5.74
     Senegal
    5.54
     Maid
    4.74
     Mb
    4.74
     Mali
    4.65
    Activations Density 0.028%

    No Known Activations