© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21806
    Prev
    Next
    INDEX
    Explanations

    copyright-related information

    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
    1:0.02
    2:0.03
    3:0.10
    4:0.04
    5:0.07
    6:0.14
    7:0.04
    8:0.10
    9:0.24
    10:0.03
    11:0.04
    Negative Logits
     Lily
    -3.64
     Sail
    -3.49
     Sense
    -3.41
     Sly
    -3.25
     sul
    -3.18
     Sally
    -3.13
     Sailor
    -3.12
     Gry
    -3.10
     inval
    -3.08
     Mori
    -3.06
    POSITIVE LOGITS
    KC
    3.77
    KR
    3.70
    Columb
    3.44
    Kenn
    3.37
    alde
    3.33
    Keefe
    3.30
    KT
    3.29
    ansas
    3.23
    Center
    3.22
    キ
    3.21
    Activations Density 0.000%

    No Known Activations