© 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. 28604
    Prev
    Next
    INDEX
    Explanations

    words associated with specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.04
    6:0.40
    7:0.04
    8:0.05
    9:0.08
    10:0.07
    11:0.06
    Negative Logits
    itious
    -1.29
    hement
    -1.26
    igning
    -1.26
    advertising
    -1.17
     nurture
    -1.16
    uador
    -1.15
     action
    -1.13
     discrim
    -1.07
    angelo
    -1.06
     pedoph
    -1.06
    POSITIVE LOGITS
    �
    1.38
    abi
    1.33
    urat
    1.27
    yna
    1.26
    ftime
    1.24
     Neh
    1.24
    �
    1.23
    enei
    1.23
    obin
    1.23
    schild
    1.21
    Activations Density 0.009%

    No Known Activations