© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22838
    Prev
    Next
    INDEX
    Explanations

    technical and technology-related information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words describing industrial processes and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    2:0.16
    3:0.09
    4:0.02
    5:0.11
    6:0.08
    7:0.05
    8:0.05
    9:0.15
    10:0.10
    11:0.04
    Negative Logits
    ツ
    -1.51
    .")
    -1.27
    ケ
    -1.25
    龍�
    -1.25
    KEN
    -1.23
    umatic
    -1.22
    ONSORED
    -1.22
    Bey
    -1.19
    ビ
    -1.15
    INTON
    -1.14
    POSITIVE LOGITS
     themselves
    1.15
     abound
    1.14
     Earthqu
    1.09
     grouped
    1.07
     FT
    1.07
     Tamil
    1.06
     alike
    1.03
     converge
    1.02
     Daryl
    1.02
     gathered
    1.01
    Activations Density 0.528%

    No Known Activations