© 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. 28037
    Prev
    Next
    INDEX
    Explanations

    instances of the word "no" associated with refusals or negative responses

    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
    0:0.03
    1:0.01
    2:0.09
    3:0.05
    4:0.13
    5:0.03
    6:0.07
    7:0.34
    8:0.04
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     largeDownload
    -1.73
    lance
    -1.64
    Spread
    -1.63
    quartered
    -1.57
    Winged
    -1.57
    ゼウス
    -1.55
    andise
    -1.52
     Annotations
    -1.51
    aunder
    -1.49
    Appearance
    -1.49
    POSITIVE LOGITS
     blockers
    1.54
     submissions
    1.53
     rejected
    1.45
     proposals
    1.44
    olean
    1.44
     affirmative
    1.43
     objection
    1.43
     deserving
    1.41
     rejection
    1.41
    gging
    1.40
    Activations Density 0.006%

    No Known Activations