© 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. 12262
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and words that suggest interaction or invitation

    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
    0:0.11
    1:0.03
    2:0.10
    3:0.09
    4:0.07
    5:0.03
    6:0.08
    7:0.27
    8:0.02
    9:0.06
    10:0.03
    11:0.06
    Negative Logits
    Loader
    -2.22
    charg
    -2.08
    Laun
    -2.04
     Cot
    -2.01
    Je
    -1.89
    Termin
    -1.86
     Corrections
    -1.83
    Unix
    -1.81
     Hew
    -1.79
    drawn
    -1.76
    POSITIVE LOGITS
     binge
    2.64
     replay
    2.24
     Leg
    2.06
     spoiler
    2.04
    avorite
    2.02
     spoil
    1.95
     Ronaldo
    1.93
    anth
    1.90
     Spoiler
    1.90
     EG
    1.88
    Activations Density 0.036%

    No Known Activations