© 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. 2612
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating significant changes in context or scenario

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.07
    4:0.08
    5:0.02
    6:0.42
    7:0.07
    8:0.03
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
    oft
    -1.30
    enta
    -1.27
    assin
    -1.26
    tein
    -1.26
    ulin
    -1.22
    cre
    -1.21
    finger
    -1.19
    cross
    -1.18
    phal
    -1.17
    itone
    -1.14
    POSITIVE LOGITS
    nesday
    1.59
     Ramadan
    1.34
     �
    1.19
     spac
    1.18
     thous
    1.17
    enment
    1.16
    �
    1.14
     Recomm
    1.12
     EDT
    1.12
    ……
    1.12
    Activations Density 0.034%

    No Known Activations