© 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. 2-ATT-KK
    6. 21419
    Prev
    Next
    INDEX
    Explanations

    the word "about" in various contexts, indicating discussions or thoughts related to a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.15
    3:0.05
    4:0.26
    5:0.04
    6:0.02
    7:0.02
    8:0.18
    9:0.08
    10:0.05
    11:0.02
    Negative Logits
    adra
    -1.37
    ante
    -1.33
    announced
    -1.31
     reminder
    -1.24
    killed
    -1.19
    DN
    -1.18
     stip
    -1.18
     redistributed
    -1.18
    note
    -1.15
     introduced
    -1.15
    POSITIVE LOGITS
     aloud
    1.96
     srfAttach
    1.46
    pheus
    1.44
    hower
    1.44
    ��
    1.38
    nesota
    1.36
     Citiz
    1.36
    blers
    1.35
    orney
    1.31
     designing
    1.31
    Activations Density 0.010%

    No Known Activations