© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43073
    Prev
    Next
    INDEX
    Explanations

    references to political leaders and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.09
    4:0.06
    5:0.09
    6:0.03
    7:0.03
    8:0.04
    9:0.14
    10:0.28
    11:0.07
    Negative Logits
    iott
    -1.28
    Reilly
    -1.23
    leck
    -1.22
     stunt
    -1.21
     attribut
    -1.21
     err
    -1.21
    itbart
    -1.20
     RAND
    -1.20
    lees
    -1.20
     Konami
    -1.19
    POSITIVE LOGITS
     Confederation
    1.75
     annexed
    1.65
     Latvia
    1.65
     sovereignty
    1.51
    Population
    1.48
     Algeria
    1.45
     borders
    1.44
     Bolivia
    1.44
     Argentina
    1.42
     Croatia
    1.41
    Activations Density 0.794%

    No Known Activations