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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28769
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mind" indicating considerations or intentions

    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
    0:0.01
    1:0.01
    2:0.12
    3:0.06
    4:0.10
    5:0.03
    6:0.06
    7:0.37
    8:0.04
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
    acebook
    -1.83
    clerosis
    -1.52
    imeo
    -1.52
    anon
    -1.50
     Shoals
    -1.49
    rums
    -1.48
     VIDEOS
    -1.48
    philis
    -1.47
    ipel
    -1.47
    inters
    -1.46
    POSITIVE LOGITS
     lofty
    1.50
     expectations
    1.42
     strategic
    1.37
     ausp
    1.35
     honour
    1.33
     criteria
    1.33
     decor
    1.33
     recommending
    1.32
     unrealistic
    1.32
     hiring
    1.32
    Activations Density 0.003%

    No Known Activations