Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27965
    Prev
    Next
    INDEX
    Explanations

    suffixes or endings commonly associated with certain word types

    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
    1:0.06
    2:0.05
    3:0.06
    4:0.04
    5:0.06
    6:0.39
    7:0.03
    8:0.05
    9:0.06
    10:0.07
    11:0.06
    Negative Logits
    advertising
    -1.45
    yip
    -1.44
     commissions
    -1.25
    spoken
    -1.22
    mot
    -1.21
     minded
    -1.21
    rolling
    -1.19
     tackling
    -1.19
    Reviewed
    -1.17
     Egyptians
    -1.15
    POSITIVE LOGITS
    ドラゴン
    1.67
    ados
    1.62
    ikuman
    1.53
    �
    1.41
    EVA
    1.40
    ADRA
    1.40
    arie
    1.39
     Bundy
    1.39
    ナ
    1.38
    �
    1.37
    Activations Density 0.009%

    No Known Activations