© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21788
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a reduction or decrease in some context

    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
    0:0.06
    1:0.03
    2:0.12
    3:0.07
    4:0.08
    5:0.07
    6:0.03
    7:0.04
    8:0.28
    9:0.08
    10:0.06
    11:0.03
    Negative Logits
    soDeliveryDate
    -1.37
     regrets
    -1.34
     regretted
    -1.30
    guards
    -1.29
     authenticated
    -1.29
    ilan
    -1.27
    pak
    -1.26
    ourage
    -1.25
     editors
    -1.21
     Supervisor
    -1.18
    POSITIVE LOGITS
     corrosion
    1.35
     fps
    1.32
    ernaut
    1.30
    anke
    1.29
    fps
    1.22
    iferation
    1.18
    ivism
    1.16
    ゼ
    1.16
    apeake
    1.13
    xon
    1.11
    Activations Density 0.010%

    No Known Activations