© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6442
    Prev
    Next
    INDEX
    Explanations

    instances of strong affirmations or powerful statements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.06
    2:0.02
    3:0.04
    4:0.04
    5:0.05
    6:0.01
    7:0.02
    8:0.31
    9:0.01
    10:0.02
    11:0.37
    Negative Logits
    ­
    -5.67
    ADVERTISEMENT
    -5.03
     …
    -4.38
     —
    -4.22
    ‐
    -4.22
     ­
    -4.16
    aukee
    -4.03
    ….
    -4.00
    ♦
    -3.89
    —-
    -3.87
    POSITIVE LOGITS
    ",
    4.81
     -
    4.70
     (£
    4.69
    BBC
    4.46
     BBC
    4.41
    ".
    4.28
     ",
    4.17
    !".
    4.08
     apologised
    3.99
     recognise
    3.94
    Activations Density 0.002%

    No Known Activations