© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 21992
    Prev
    Next
    INDEX
    Explanations

    instances of the word "deserve" and expressions of conditional phrases or obligations

    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
    0:0.03
    1:0.43
    2:0.03
    3:0.06
    4:0.04
    5:0.04
    6:0.04
    7:0.11
    8:0.03
    9:0.08
    10:0.03
    11:0.03
    Negative Logits
    --+
    -2.52
    pox
    -2.37
    518
    -2.36
    Includes
    -2.32
    zn
    -2.23
    alse
    -2.17
     eater
    -2.16
    ogl
    -2.15
     --------------------
    -2.14
    roll
    -2.13
    POSITIVE LOGITS
     third
    7.97
    Third
    7.48
     second
    6.72
    third
    6.50
     fourth
    6.41
    second
    6.41
     Third
    5.89
     secondly
    5.50
    fourth
    5.48
    Fourth
    5.37
    Activations Density 0.027%

    No Known Activations