© 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. 18832
    Prev
    Next
    INDEX
    Explanations

    phrases related to being "better off" in various contexts, particularly in relation to financial and social conditions

    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
    0:0.04
    1:0.02
    2:0.07
    3:0.19
    4:0.03
    5:0.08
    6:0.02
    7:0.05
    8:0.05
    9:0.02
    10:0.34
    11:0.03
    Negative Logits
    catentry
    -2.19
    interstitial
    -2.14
     motif
    -1.91
     trope
    -1.88
    CVE
    -1.88
     hallmark
    -1.87
     enorm
    -1.83
    idth
    -1.74
    udicrous
    -1.72
     apex
    -1.71
    POSITIVE LOGITS
     wiser
    2.05
    essors
    1.96
     sooner
    1.95
    rek
    1.91
     hereafter
    1.90
     happier
    1.81
    zbollah
    1.81
     prevailed
    1.79
    ardless
    1.77
    bernatorial
    1.76
    Activations Density 0.008%

    No Known Activations