© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 11858
    Prev
    Next
    INDEX
    Explanations

    phrases related to family relationships

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

    references to significant entities or concepts related to representation and responsibility

    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
    1:0.05
    2:0.19
    3:0.06
    4:0.01
    5:0.08
    6:0.08
    7:0.07
    8:0.13
    9:0.09
    10:0.09
    11:0.06
    Negative Logits
    EMA
    -1.34
    ���
    -1.31
    ��
    -1.25
    Semitism
    -1.20
    ija
    -1.15
     Sao
    -1.12
    amation
    -1.12
    �
    -1.12
    anooga
    -1.06
    ENCY
    -1.04
    POSITIVE LOGITS
    agonists
    1.58
     equivalents
    1.34
     ones
    1.33
    liest
    1.32
    weights
    1.27
     respectively
    1.26
     themselves
    1.26
    luster
    1.24
     respective
    1.23
    arters
    1.17
    Activations Density 0.103%

    No Known Activations