© 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. 5-ATT-KK
    11. 6629
    Prev
    Next
    INDEX
    Explanations

    the phrase "going to" indicating future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.20
    2:0.03
    3:0.03
    4:0.02
    5:0.21
    6:0.04
    7:0.02
    8:0.05
    9:0.05
    10:0.04
    11:0.09
    Negative Logits
     Helic
    -1.70
     UCS
    -1.64
     sqor
    -1.58
     Cornell
    -1.51
     hob
    -1.50
    eton
    -1.48
     Rutgers
    -1.47
    atform
    -1.47
    rament
    -1.46
     IBM
    -1.45
    POSITIVE LOGITS
    ْ
    2.27
    Stretch
    2.02
    Rules
    1.96
    َ
    1.93
    黒
    1.90
    dating
    1.90
    2018
    1.84
    Ability
    1.81
    steam
    1.81
    Release
    1.79
    Activations Density 0.008%

    No Known Activations