© 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. 35356
    Prev
    Next
    INDEX
    Explanations

    content related to political and economic entities or principles

    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
    0:0.08
    1:0.02
    2:0.11
    3:0.14
    4:0.21
    5:0.04
    6:0.05
    7:0.03
    8:0.06
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
    avascript
    -1.52
    withstanding
    -1.45
     coincides
    -1.43
     Canaver
    -1.43
    utterstock
    -1.42
    ypes
    -1.41
     coincided
    -1.41
    efer
    -1.38
    heet
    -1.35
    early
    -1.32
    POSITIVE LOGITS
     etc
    2.09
    fax
    1.66
    etc
    1.38
    rosis
    1.30
     blah
    1.30
     circ
    1.26
    ativity
    1.24
     Acquisition
    1.24
     continents
    1.23
    inking
    1.21
    Activations Density 0.346%

    No Known Activations