© 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. 9-ATT-KK
    11. 2783
    Prev
    Next
    INDEX
    Explanations

    mentions of films and their release years

    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
    0:0.06
    1:0.16
    2:0.02
    3:0.07
    4:0.05
    5:0.18
    6:0.09
    7:0.05
    8:0.05
    9:0.04
    10:0.04
    11:0.14
    Negative Logits
     ninety
    -2.45
     filler
    -2.40
     surv
    -2.30
     improvement
    -2.28
     59
    -2.28
     parity
    -2.26
     rece
    -2.22
     elapsed
    -2.19
     45
    -2.19
     88
    -2.18
    POSITIVE LOGITS
    2011
    2.55
    2008
    2.49
    2009
    2.46
    2010
    2.46
    2006
    2.43
    2019
    2.41
    1972
    2.40
    Definition
    2.39
    WN
    2.36
    2007
    2.35
    Activations Density 0.003%

    No Known Activations