© 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. 18276
    Prev
    Next
    INDEX
    Explanations

    elements related to legal and copyright issues

    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
    0:0.10
    1:0.04
    2:0.08
    3:0.03
    4:0.06
    5:0.04
    6:0.18
    7:0.07
    8:0.06
    9:0.21
    10:0.03
    11:0.05
    Negative Logits
     tagging
    -3.70
    opal
    -3.67
    Tag
    -3.63
    ilan
    -3.60
     cuc
    -3.58
    tag
    -3.55
    ça
    -3.41
     squid
    -3.38
     anten
    -3.34
    fruit
    -3.33
    POSITIVE LOGITS
     Holmes
    10.29
    Hol
    7.02
     Watson
    4.84
     Sherlock
    4.66
     Doyle
    4.54
    hol
    4.39
     Hol
    4.22
     Aurora
    3.98
    azes
    3.98
     HOL
    3.97
    Activations Density 0.002%

    No Known Activations