© 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. 10889
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate repetition or consistency

    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
    0:0.01
    1:0.05
    2:0.16
    3:0.02
    4:0.01
    5:0.03
    6:0.13
    7:0.15
    8:0.05
    9:0.09
    10:0.10
    11:0.15
    Negative Logits
    estamp
    -1.31
    ocaust
    -1.28
    ogram
    -1.25
    oval
    -1.21
    olitical
    -1.20
    ueless
    -1.18
    olithic
    -1.18
    ologue
    -1.17
    maxwell
    -1.15
    ablished
    -1.14
    POSITIVE LOGITS
    Cole
    1.15
    ンジ
    1.04
     hackers
    0.99
    ••••
    0.98
     imaginable
    0.97
     membr
    0.97
     offenders
    0.97
    groupon
    0.96
     reimbursement
    0.96
     strains
    0.94
    Activations Density 0.017%

    No Known Activations