© 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. 37651
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a call to action or suggestions for progress

    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
    0:0.11
    1:0.06
    2:0.05
    3:0.05
    4:0.05
    5:0.22
    6:0.04
    7:0.04
    8:0.15
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    phrase
    -2.22
    emen
    -2.18
    atable
    -1.91
    dra
    -1.89
    erb
    -1.86
    estones
    -1.86
    ppings
    -1.84
    ô
    -1.80
    és
    -1.79
    uran
    -1.77
    POSITIVE LOGITS
     hemor
    2.21
     anx
    1.98
     slowing
    1.97
    ��
    1.91
     exting
    1.85
     earthqu
    1.84
     rever
    1.82
     boycot
    1.82
     thirst
    1.80
     quitting
    1.80
    Activations Density 0.004%

    No Known Activations