© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2394
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights and freedom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.09
    3:0.05
    4:0.06
    5:0.03
    6:0.35
    7:0.03
    8:0.03
    9:0.03
    10:0.12
    11:0.11
    Negative Logits
    ouver
    -1.35
    iculty
    -1.34
    phrine
    -1.33
    \/\/
    -1.30
    incial
    -1.30
    govtrack
    -1.25
    itcher
    -1.25
    thumbnails
    -1.21
    soDeliveryDate
    -1.21
    UGC
    -1.18
    POSITIVE LOGITS
     Restoration
    1.26
     dwarves
    1.24
     capacitor
    1.22
     unification
    1.22
    tein
    1.19
     gorilla
    1.17
     Speedway
    1.13
     homeland
    1.13
     millennium
    1.11
     elegance
    1.10
    Activations Density 0.011%

    No Known Activations