© 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. 3031
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial statistics

    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
    2:0.04
    3:0.13
    4:0.02
    5:0.06
    6:0.02
    7:0.04
    8:0.04
    9:0.03
    10:0.48
    11:0.03
    Negative Logits
     correctly
    -2.32
     steadily
    -2.25
     wrongly
    -2.24
     underlying
    -2.22
     owing
    -2.18
     unexpectedly
    -2.12
     ascending
    -2.06
     narrowing
    -2.02
     descending
    -2.01
     lately
    -2.00
    POSITIVE LOGITS
    )).
    2.17
    ranged
    2.09
    ))
    1.98
    )))
    1.95
    ]).
    1.94
    aughs
    1.91
    pert
    1.91
    chuk
    1.89
     entertain
    1.82
    orage
    1.80
    Activations Density 0.008%

    No Known Activations