© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 14240
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts or refusal to make concessions for peace

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases that emphasize purpose or intent, particularly centered around the phrase "for the sake of."

    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
    1:0.02
    2:0.07
    3:0.33
    4:0.02
    5:0.02
    6:0.06
    7:0.10
    8:0.06
    9:0.09
    10:0.06
    11:0.10
    Negative Logits
    IFIED
    -1.38
    ilogy
    -1.36
    addle
    -1.36
    abase
    -1.35
    isable
    -1.34
    throp
    -1.34
    izable
    -1.32
    atform
    -1.28
    azo
    -1.24
    organic
    -1.23
    POSITIVE LOGITS
     sake
    1.40
    irin
    1.31
     hindsight
    1.28
     restart
    1.14
     simplicity
    1.13
     aver
    1.12
     persuasion
    1.10
     hunger
    1.06
     juices
    1.06
     punishments
    1.05
    Activations Density 0.002%

    No Known Activations