© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing causal relationships or conditions

    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
    1:0.04
    2:0.06
    3:0.05
    4:0.02
    5:0.04
    6:0.04
    7:0.06
    8:0.07
    9:0.41
    10:0.07
    11:0.05
    Negative Logits
    ��
    -1.62
    rack
    -1.45
     DEFENSE
    -1.42
     srfAttach
    -1.39
    ENTION
    -1.38
    iolet
    -1.38
    ildo
    -1.37
    oor
    -1.36
    rar
    -1.33
    Reviewer
    -1.33
    POSITIVE LOGITS
     surn
    1.31
     fists
    1.23
    few
    1.21
    reflect
    1.19
     toget
    1.17
     postp
    1.14
     fist
    1.12
    fights
    1.11
     momentarily
    1.10
     kindred
    1.10
    Activations Density 0.023%

    No Known Activations