© 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. 43273
    Prev
    Next
    INDEX
    Explanations

    entities and organizations relevant to politics and economics

    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
    0:0.05
    1:0.01
    2:0.15
    3:0.19
    4:0.10
    5:0.03
    6:0.03
    7:0.03
    8:0.06
    9:0.06
    10:0.12
    11:0.10
    Negative Logits
    minist
    -1.63
     DOES
    -1.60
    RAFT
    -1.56
     compromises
    -1.54
     dogma
    -1.54
     doesnt
    -1.53
     cannot
    -1.52
     resolves
    -1.50
     contradicts
    -1.48
    ][/
    -1.47
    POSITIVE LOGITS
     honorary
    1.53
     Bing
    1.47
     Hels
    1.44
     Cheong
    1.44
     assorted
    1.43
     Bei
    1.37
     haw
    1.35
     pse
    1.33
     Sahara
    1.29
     elder
    1.28
    Activations Density 0.280%

    No Known Activations