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

    Neuronpedia

    Jacobian LensNEW
    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. 9-ATT-KK
    11. 8488
    Prev
    Next
    INDEX
    Explanations

    expressions related to actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.05
    2:0.11
    3:0.06
    4:0.03
    5:0.04
    6:0.21
    7:0.04
    8:0.04
    9:0.24
    10:0.04
    11:0.02
    Negative Logits
     Bates
    -3.71
     acupuncture
    -3.70
     Byrne
    -3.62
    IRC
    -3.58
     Fischer
    -3.47
     Cunningham
    -3.40
    ambers
    -3.36
     needles
    -3.24
     Akin
    -3.19
    FN
    -3.18
    POSITIVE LOGITS
     Destruction
    6.85
    Destroy
    6.78
    destroy
    6.66
     Destroy
    6.43
     destruction
    6.30
     destroy
    6.26
     Destroyer
    6.14
    Dest
    6.11
     destroying
    6.05
     destroys
    6.01
    Activations Density 0.002%

    No Known Activations