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

    Neuronpedia

    APICircuit 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. 8369
    Prev
    Next
    INDEX
    Explanations

    specific locations and activities related to training or community engagement

    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
    0:0.02
    1:0.04
    2:0.11
    3:0.04
    4:0.01
    5:0.03
    6:0.05
    7:0.13
    8:0.25
    9:0.08
    10:0.06
    11:0.10
    Negative Logits
    eness
    -1.12
     bothered
    -1.05
    etheless
    -1.02
     ¶
    -1.01
    ¯¯
    -1.01
    enance
    -0.99
    pecting
    -0.99
     Logged
    -0.99
     ===
    -0.98
     Swed
    -0.97
    POSITIVE LOGITS
    orage
    1.28
    iann
    1.22
    alia
    1.22
    anya
    1.18
    akura
    1.17
    meet
    1.17
    ettlement
    1.16
     graduation
    1.15
    uberty
    1.13
    School
    1.11
    Activations Density 0.028%

    No Known Activations