© 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. 41755
    Prev
    Next
    INDEX
    Explanations

    instances of individuals and their associated numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.19
    3:0.05
    4:0.12
    5:0.03
    6:0.05
    7:0.02
    8:0.06
    9:0.06
    10:0.13
    11:0.19
    Negative Logits
    iners
    -1.42
    mbuds
    -1.37
     Fathers
    -1.35
     Churches
    -1.32
    ieties
    -1.28
    yles
    -1.26
    iculture
    -1.25
    iries
    -1.24
    olon
    -1.23
     fellowship
    -1.23
    POSITIVE LOGITS
     livest
    1.48
    bold
    1.23
     maneu
    1.21
    gross
    1.21
    Ranked
    1.19
    adj
    1.18
    withstanding
    1.18
    lived
    1.17
     nicknamed
    1.17
     defied
    1.16
    Activations Density 0.029%

    No Known Activations