© 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. 27636
    Prev
    Next
    INDEX
    Explanations

    phrases that involve direct speech, particularly those that convey important statements or sentiments

    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
    2:0.24
    3:0.06
    4:0.10
    5:0.02
    6:0.03
    7:0.16
    8:0.06
    9:0.03
    10:0.07
    11:0.12
    Negative Logits
    etter
    -1.55
     AJ
    -1.35
     resear
    -1.34
     Hak
    -1.32
     ransom
    -1.31
     editor
    -1.29
     keynote
    -1.27
    iga
    -1.26
     Benedict
    -1.24
     christ
    -1.24
    POSITIVE LOGITS
    interstitial
    2.19
    NetMessage
    1.82
    ��
    1.59
    ////////////////
    1.56
    ntil
    1.52
    Temperature
    1.47
    shed
    1.43
    leness
    1.40
    lest
    1.40
    WHERE
    1.39
    Activations Density 0.008%

    No Known Activations