© 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. 10-ATT-KK
    11. 20494
    Prev
    Next
    INDEX
    Explanations

    references to unhealthy fats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.46
    2:0.05
    3:0.06
    4:0.04
    5:0.04
    6:0.03
    7:0.07
    8:0.06
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
     Moderate
    -2.73
     compounded
    -2.70
     Equal
    -2.70
    igible
    -2.62
     Dou
    -2.60
     OW
    -2.56
     Progressive
    -2.53
     Heavy
    -2.46
    owl
    -2.43
     fore
    -2.42
    POSITIVE LOGITS
     around
    5.97
     Around
    5.63
    around
    5.40
    Around
    4.86
     round
    4.01
    round
    3.64
     surrounds
    3.48
    Round
    3.39
    near
    3.39
     surrounding
    3.25
    Activations Density 0.056%

    No Known Activations