© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 2599
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to common sense and logical reasoning in various contexts

    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
    0:0.03
    1:0.01
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.43
    7:0.10
    8:0.02
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
    eki
    -2.11
    ��
    -1.66
    omo
    -1.49
     landfall
    -1.43
    icho
    -1.41
    etus
    -1.39
    ══
    -1.34
     Papa
    -1.32
    assium
    -1.31
    psey
    -1.30
    POSITIVE LOGITS
    rities
    1.78
    ourses
    1.74
    urses
    1.52
    ATIONS
    1.50
    rences
    1.44
    cill
    1.41
    views
    1.40
    ilings
    1.37
    illance
    1.33
    ensical
    1.33
    Activations Density 0.009%

    No Known Activations