© 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. 35535
    Prev
    Next
    INDEX
    Explanations

    negations or refusals in statements

    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
    0:0.04
    1:0.01
    2:0.12
    3:0.14
    4:0.07
    5:0.03
    6:0.05
    7:0.11
    8:0.04
    9:0.06
    10:0.15
    11:0.11
    Negative Logits
    yre
    -1.44
    imer
    -1.39
     frontline
    -1.35
    lling
    -1.31
    gow
    -1.30
     adversaries
    -1.25
    soDeliveryDate
    -1.24
    ogun
    -1.23
    asers
    -1.23
    anus
    -1.22
    POSITIVE LOGITS
     appre
    1.65
     Cancel
    1.50
     Moder
    1.43
    ウス
    1.42
    エル
    1.35
     Comments
    1.32
    Reviewed
    1.31
     Published
    1.30
     Terms
    1.29
     Cannot
    1.29
    Activations Density 0.000%

    No Known Activations