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

    Neuronpedia

    Jacobian LensNEW
    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. 7695
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time-sensitive events or limitations

    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
    1:0.02
    2:0.13
    3:0.19
    4:0.08
    5:0.02
    6:0.17
    7:0.03
    8:0.07
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
    udi
    -1.40
    ievers
    -1.18
    aunders
    -1.10
    ogie
    -1.10
    cknow
    -1.09
     ];
    -1.09
     Franco
    -1.08
    /"
    -1.07
    college
    -1.06
     contrace
    -1.05
    POSITIVE LOGITS
     downright
    1.30
     itself
    1.27
     quite
    1.21
    marked
    1.16
     thereafter
    1.16
     pretty
    1.14
    oya
    1.14
    フ
    1.14
    encia
    1.13
    initely
    1.12
    Activations Density 0.090%

    No Known Activations