© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40426
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proximity or closeness

    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
    0:0.02
    1:0.03
    2:0.10
    3:0.04
    4:0.10
    5:0.02
    6:0.11
    7:0.33
    8:0.02
    9:0.02
    10:0.06
    11:0.10
    Negative Logits
    EMS
    -1.57
     frustration
    -1.53
    Charges
    -1.45
    sbm
    -1.43
    estyles
    -1.37
    の�
    -1.36
     millenn
    -1.36
    soever
    -1.34
    ious
    -1.33
    acks
    -1.32
    POSITIVE LOGITS
     Enemy
    1.54
     latitude
    1.42
     Leigh
    1.40
    thood
    1.35
    kiss
    1.35
     Spectre
    1.34
     RIS
    1.30
     orbit
    1.29
     FRI
    1.29
     disliked
    1.27
    Activations Density 0.012%

    No Known Activations