© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17875
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions indicating the relationship between subjects and their actions or descriptors

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.04
    4:0.05
    5:0.03
    6:0.14
    7:0.03
    8:0.05
    9:0.43
    10:0.02
    11:0.02
    Negative Logits
     Pelosi
    -3.48
    otin
    -3.44
    rupal
    -3.38
     Lilith
    -3.35
    len
    -3.34
    uca
    -3.33
     hemp
    -3.27
     Huck
    -3.26
     Frie
    -3.26
    anners
    -3.25
    POSITIVE LOGITS
     James
    8.36
    James
    8.07
     Jays
    4.38
    ames
    4.38
    AMES
    4.18
     Irving
    4.18
    Jim
    3.78
    JR
    3.67
     Jim
    3.65
    Sir
    3.61
    Activations Density 0.022%

    No Known Activations