© 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. 13645
    Prev
    Next
    INDEX
    Explanations

    references to films and games, particularly those known for their impact or popularity

    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
    0:0.04
    1:0.04
    2:0.03
    3:0.17
    4:0.03
    5:0.06
    6:0.02
    7:0.05
    8:0.04
    9:0.02
    10:0.43
    11:0.03
    Negative Logits
     unspecified
    -2.44
    田
    -2.01
     understatement
    -1.93
     premises
    -1.88
     thereafter
    -1.88
     unwitting
    -1.85
     FIRST
    -1.80
     underside
    -1.77
     shortly
    -1.77
     debut
    -1.75
    POSITIVE LOGITS
    rir
    2.10
    neys
    2.06
     or
    2.04
     nor
    2.00
    Rich
    1.97
    better
    1.92
    ®,
    1.91
    /,
    1.86
     anymore
    1.85
     prefers
    1.83
    Activations Density 0.194%

    No Known Activations