© 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. 9-ATT-KK
    11. 2964
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of the soul and its condition

    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
    0:0.27
    1:0.02
    2:0.17
    3:0.11
    4:0.03
    5:0.07
    6:0.03
    7:0.07
    8:0.06
    9:0.01
    10:0.08
    11:0.02
    Negative Logits
    TeX
    -2.38
     SVG
    -2.34
     PowerPoint
    -2.31
     Tactics
    -2.27
     escalate
    -2.19
     Zup
    -2.16
    andowski
    -2.16
     Brus
    -2.15
    ORPG
    -2.12
     erg
    -2.11
    POSITIVE LOGITS
     Purg
    3.40
     departed
    3.21
     soul
    3.09
    rieve
    3.03
     souls
    2.93
     forfeit
    2.85
    Soul
    2.83
     crem
    2.83
     Soul
    2.81
     disemb
    2.75
    Activations Density 0.002%

    No Known Activations