© 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. 22835
    Prev
    Next
    INDEX
    Explanations

    information related to diverse topics, including slavery, military procedures, legal actions, government appointments, and human rights issues

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

    instances of authority and decision-making in various contexts

    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
    1:0.22
    2:0.03
    3:0.04
    4:0.03
    5:0.04
    6:0.07
    7:0.10
    8:0.04
    9:0.06
    10:0.15
    11:0.08
    Negative Logits
    uliffe
    -2.04
    espie
    -2.02
    esville
    -1.83
     campaigner
    -1.78
    cffff
    -1.75
     persecut
    -1.73
     elig
    -1.72
    accompan
    -1.66
     campaigning
    -1.64
    gettable
    -1.64
    POSITIVE LOGITS
    canon
    2.27
     Luffy
    2.20
     Unicode
    2.17
     �
    2.03
     XD
    2.00
     Goku
    1.97
    Shin
    1.97
     �
    1.96
    ˈ
    1.94
    Tang
    1.93
    Activations Density 0.252%

    No Known Activations