Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22582
    Prev
    Next
    INDEX
    Explanations

    key phrases related to legal matters, environmental issues, and community actions

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

    phrases related to campaigns and promotional offers

    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
    0:0.10
    1:0.02
    2:0.12
    3:0.08
    4:0.07
    5:0.05
    6:0.05
    7:0.06
    8:0.14
    9:0.13
    10:0.08
    11:0.03
    Negative Logits
    dn
    -1.19
    nar
    -1.15
    rouch
    -1.15
    ön
    -1.14
    rower
    -1.12
    iday
    -1.08
    aeper
    -1.07
    isch
    -1.06
    cfg
    -1.04
    ��
    -1.04
    POSITIVE LOGITS
     Yourself
    1.28
     yourselves
    1.25
     Seasons
    1.17
     Sanctuary
    1.17
     Carbuncle
    1.17
     Barg
    1.13
     Bees
    1.12
     Shares
    1.11
     Kingdoms
    1.08
    BuyableInstoreAndOnline
    1.07
    Activations Density 0.005%

    No Known Activations