© 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. 22811
    Prev
    Next
    INDEX
    Explanations

    numbers indicating quantities and statistics

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

    quantitative data and statistics related to elections, population, and budgets

    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
    1:0.05
    2:0.06
    3:0.13
    4:0.04
    5:0.12
    6:0.07
    7:0.05
    8:0.08
    9:0.09
    10:0.13
    11:0.05
    Negative Logits
    Gameplay
    -1.35
    �
    -1.31
    webkit
    -1.30
     spoilers
    -1.23
    forward
    -1.13
    NetMessage
    -1.05
     regret
    -1.03
    Appearance
    -1.03
     unfocusedRange
    -1.02
    ODY
    -1.02
    POSITIVE LOGITS
    iest
    1.68
    osphere
    1.40
     Poverty
    1.40
     economy
    1.39
     workforce
    1.35
    owment
    1.34
     population
    1.30
     equivalent
    1.26
     Industrial
    1.20
    liest
    1.20
    Activations Density 0.164%

    No Known Activations