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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10175
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to laws, regulations, and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.06
    2:0.10
    3:0.03
    4:0.07
    5:0.05
    6:0.11
    7:0.25
    8:0.05
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
    etheless
    -1.69
     confir
    -1.68
     agre
    -1.67
    irez
    -1.64
     streng
    -1.62
    anwhile
    -1.62
    yss
    -1.61
    ��極
    -1.57
    awaru
    -1.55
     acknow
    -1.54
    POSITIVE LOGITS
     Bre
    1.25
    Bre
    1.21
    ヘ
    1.18
    onics
    1.17
    ials
    1.13
    tones
    1.13
     implants
    1.09
    grain
    1.08
     parity
    1.08
    Crystal
    1.08
    Activations Density 0.682%

    No Known Activations