© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19549
    Prev
    Next
    INDEX
    Explanations

    phrases related to analysis and comparison of literary works or thematic discussions

    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
    0:0.01
    1:0.01
    2:0.24
    3:0.14
    4:0.12
    5:0.03
    6:0.04
    7:0.10
    8:0.04
    9:0.03
    10:0.11
    11:0.06
    Negative Logits
    zan
    -1.27
     neighbor
    -1.26
    egu
    -1.25
    odan
    -1.24
    ilingual
    -1.20
    wy
    -1.19
    uria
    -1.19
    insk
    -1.19
     brakes
    -1.18
    uph
    -1.17
    POSITIVE LOGITS
     Including
    1.87
    APTER
    1.66
    ixt
    1.47
     COVER
    1.43
     TEAM
    1.40
     includ
    1.40
    Roger
    1.35
     DIRECT
    1.34
    including
    1.33
    ÍÍ
    1.31
    Activations Density 0.065%

    No Known Activations