© 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. 3-ATT-KK
    11. 13419
    Prev
    Next
    INDEX
    Explanations

    strong positive statements or assertions

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

    phrases that include the verb "is" in various contexts

    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
    1:0.07
    2:0.08
    3:0.13
    4:0.02
    5:0.02
    6:0.15
    7:0.04
    8:0.09
    9:0.14
    10:0.11
    11:0.08
    Negative Logits
    cair
    -0.95
    amines
    -0.88
    cape
    -0.84
     Diary
    -0.79
    OX
    -0.77
    \">
    -0.76
    haul
    -0.74
    \/\/
    -0.74
    Malley
    -0.73
    ieu
    -0.73
    POSITIVE LOGITS
     parap
    0.80
     defe
    0.79
     teleport
    0.79
     honorary
    0.76
    cipline
    0.76
    warm
    0.75
     firsthand
    0.74
     lapse
    0.74
     blat
    0.74
    ground
    0.73
    Activations Density 0.013%

    No Known Activations