© 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. 22722
    Prev
    Next
    INDEX
    Explanations

    information related to government treaties, laws, and provisions

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

    verbs and phrases that describe actions related to change, progress, or challenges

    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
    1:0.02
    2:0.07
    3:0.08
    4:0.04
    5:0.14
    6:0.04
    7:0.07
    8:0.13
    9:0.08
    10:0.14
    11:0.07
    Negative Logits
    Favorite
    -0.91
    SPONSORED
    -0.91
    Movie
    -0.76
    itty
    -0.76
     dolphin
    -0.76
    TM
    -0.75
    MSN
    -0.74
     dude
    -0.73
     mixer
    -0.73
    ♥
    -0.71
    POSITIVE LOGITS
     lately
    1.02
    leases
    0.94
    ecause
    0.94
     precedent
    0.92
    arbon
    0.90
     considerably
    0.88
    amount
    0.88
     considerable
    0.86
    funding
    0.86
    エル
    0.86
    Activations Density 0.662%

    No Known Activations