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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 19431
    Prev
    Next
    INDEX
    Explanations

    instances of specific citations or references in academic writing

    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
    1:0.03
    2:0.05
    3:0.09
    4:0.07
    5:0.05
    6:0.13
    7:0.05
    8:0.05
    9:0.09
    10:0.16
    11:0.15
    Negative Logits
     biome
    -1.31
     tribunal
    -1.28
     pageant
    -1.27
     virginity
    -1.25
     seeker
    -1.24
     apartheid
    -1.24
     Fey
    -1.22
     Ary
    -1.21
    BuyableInstoreAndOnline
    -1.20
     Rai
    -1.20
    POSITIVE LOGITS
    ッド
    1.60
     teasp
    1.40
    ÃÂ
    1.32
    nikov
    1.31
     pione
    1.31
    ounce
    1.28
    artz
    1.23
    undo
    1.23
    ��
    1.22
    follow
    1.22
    Activations Density 0.003%

    No Known Activations