© 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. 29436
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expression or personal feelings

    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
    0:0.13
    1:0.31
    2:0.02
    3:0.02
    4:0.02
    5:0.20
    6:0.12
    7:0.01
    8:0.04
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
     scanners
    -1.64
     300
    -1.61
     350
    -1.54
     notebooks
    -1.51
     GPS
    -1.50
     340
    -1.47
     boxes
    -1.47
     �
    -1.46
    FTWARE
    -1.46
     700
    -1.45
    POSITIVE LOGITS
    d
    2.84
    dx
    2.47
    xd
    2.32
    dp
    2.27
    tan
    2.27
    dh
    2.17
    dal
    2.15
    dl
    2.14
    ei
    2.12
    vest
    2.11
    Activations Density 0.010%

    No Known Activations