© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11155
    Prev
    Next
    INDEX
    Explanations

    patterns related to online actions and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.15
    3:0.05
    4:0.02
    5:0.04
    6:0.05
    7:0.25
    8:0.09
    9:0.08
    10:0.10
    11:0.08
    Negative Logits
    orio
    -1.05
    cu
    -1.04
     Kaf
    -1.03
    ifa
    -0.94
    umper
    -0.94
    ouf
    -0.93
    amiya
    -0.92
     dwell
    -0.92
     dwelling
    -0.92
    apsed
    -0.91
    POSITIVE LOGITS
    nesday
    1.03
     guiActiveUn
    1.01
    QUIRE
    0.93
    Spoiler
    0.91
     violate
    0.91
    morning
    0.90
    anyl
    0.89
    fml
    0.89
     steroids
    0.89
    swick
    0.89
    Activations Density 0.037%

    No Known Activations