© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21380
    Prev
    Next
    INDEX
    Explanations

    words indicating change in status or condition

    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
    2:0.06
    3:0.05
    4:0.03
    5:0.09
    6:0.03
    7:0.08
    8:0.27
    9:0.05
    10:0.14
    11:0.07
    Negative Logits
     sampling
    -1.08
    BW
    -1.04
     foregoing
    -1.00
     provided
    -0.98
     cheek
    -0.94
     preceding
    -0.93
     skew
    -0.93
    VW
    -0.92
     cov
    -0.92
     behav
    -0.91
    POSITIVE LOGITS
    ��
    1.32
     fodder
    1.24
    kat
    1.15
    onel
    1.15
    zai
    1.14
    bard
    1.13
    イ
    1.12
    tier
    1.11
    effective
    1.11
    Tier
    1.10
    Activations Density 0.114%

    No Known Activations