© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22025
    Prev
    Next
    INDEX
    Explanations

    instances of reported comments or statements made by individuals

    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
    0:0.06
    1:0.04
    2:0.13
    3:0.05
    4:0.08
    5:0.10
    6:0.05
    7:0.04
    8:0.07
    9:0.22
    10:0.08
    11:0.03
    Negative Logits
    EEE
    -1.18
     dudes
    -1.13
    rients
    -1.10
    ゼウス
    -1.10
     colonies
    -1.06
     condo
    -1.05
     Tycoon
    -1.03
     droid
    -1.03
     subdiv
    -1.02
    bage
    -1.02
    POSITIVE LOGITS
     quoting
    1.47
     quotation
    1.45
     retweet
    1.35
     omission
    1.31
     sarcast
    1.29
    plain
    1.29
     speeches
    1.28
    rompt
    1.25
    yip
    1.24
     "@
    1.24
    Activations Density 0.016%

    No Known Activations