© 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. 10-ATT-KK
    11. 12539
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of control and responsibility in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.35
    2:0.04
    3:0.07
    4:0.07
    5:0.02
    6:0.08
    7:0.08
    8:0.03
    9:0.03
    10:0.04
    11:0.09
    Negative Logits
    natureconservancy
    -3.48
    龍契士
    -3.23
    byss
    -3.04
    Typ
    -2.66
     Bold
    -2.65
    hyp
    -2.61
    young
    -2.61
     pale
    -2.51
    sweet
    -2.49
    conscious
    -2.48
    POSITIVE LOGITS
     internal
    6.70
     external
    6.64
    external
    6.53
    internal
    6.47
     External
    6.38
    Internal
    6.21
    External
    5.87
     Internal
    5.81
     externally
    5.63
     internally
    4.82
    Activations Density 0.022%

    No Known Activations