© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14487
    Prev
    Next
    INDEX
    Explanations

    references to personal agency and individual actions or decisions

    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
    0:0.06
    1:0.03
    2:0.07
    3:0.19
    4:0.03
    5:0.05
    6:0.03
    7:0.05
    8:0.04
    9:0.04
    10:0.32
    11:0.04
    Negative Logits
     indign
    -2.54
     aback
    -2.41
     scorn
    -2.25
     stares
    -2.21
     incred
    -2.20
     scathing
    -2.18
     disappoint
    -2.15
     disdain
    -2.10
     dismay
    -2.10
     merciless
    -2.07
    POSITIVE LOGITS
     ideally
    3.12
     Ideally
    2.51
     preferably
    2.43
     intended
    2.42
    izable
    2.37
    Compan
    2.31
    iable
    2.29
     hoped
    2.27
     optimal
    2.25
    requ
    2.14
    Activations Density 0.006%

    No Known Activations