© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or possession

    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
    0:0.04
    1:0.02
    2:0.21
    3:0.03
    4:0.34
    5:0.04
    6:0.03
    7:0.02
    8:0.08
    9:0.09
    10:0.03
    11:0.02
    Negative Logits
    ��
    -1.87
    lr
    -1.49
    arat
    -1.46
    etheless
    -1.46
    pson
    -1.46
    iston
    -1.45
    >]
    -1.41
    rouch
    -1.40
    ��
    -1.39
    untarily
    -1.38
    POSITIVE LOGITS
    Assembly
    1.67
     Bees
    1.53
    ドラ
    1.44
    Bee
    1.35
     bee
    1.33
    GGGGGGGG
    1.32
     extraord
    1.31
    Adds
    1.29
    KNOWN
    1.27
    CLASSIFIED
    1.26
    Activations Density 0.043%

    No Known Activations