© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27664
    Prev
    Next
    INDEX
    Explanations

    the word "Don't"

    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
    0:0.08
    1:0.07
    2:0.08
    3:0.06
    4:0.07
    5:0.08
    6:0.07
    7:0.09
    8:0.08
    9:0.09
    10:0.10
    11:0.07
    Negative Logits
    ittal
    -1.91
     silence
    -1.80
    essim
    -1.75
     evacuation
    -1.70
     literacy
    -1.57
    ignt
    -1.55
     policeman
    -1.52
    othe
    -1.52
     readings
    -1.51
     reassure
    -1.50
    POSITIVE LOGITS
    ゴン
    1.82
    XP
    1.81
    大
    1.75
     respectively
    1.70
    ]}
    1.56
    brids
    1.53
     thous
    1.52
    �
    1.46
    方
    1.46
    モ
    1.45
    Activations Density 0.000%

    No Known Activations