© 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. 43657
    Prev
    Next
    INDEX
    Explanations

    instances where individuals reflect on their thoughts and feelings

    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
    0:0.01
    1:0.02
    2:0.04
    3:0.06
    4:0.08
    5:0.02
    6:0.04
    7:0.48
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    mouth
    -1.69
    ante
    -1.65
    adra
    -1.62
    Torrent
    -1.46
    tumblr
    -1.39
    ected
    -1.36
    fed
    -1.36
    eatured
    -1.35
    aredevil
    -1.35
    ioxide
    -1.32
    POSITIVE LOGITS
     aloud
    1.85
     hypot
    1.62
     nostalg
    1.57
     captcha
    1.49
     possibilities
    1.40
     nervously
    1.39
    hov
    1.39
     visions
    1.38
    paren
    1.37
     how
    1.36
    Activations Density 0.101%

    No Known Activations