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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 25250
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating contrast or transition between different ideas or points

    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
    1:0.03
    2:0.08
    3:0.10
    4:0.08
    5:0.06
    6:0.08
    7:0.14
    8:0.07
    9:0.05
    10:0.08
    11:0.16
    Negative Logits
    Tea
    -1.57
    ftime
    -1.49
     eq
    -1.39
    loe
    -1.36
    ゼウス
    -1.34
    utherland
    -1.33
    culated
    -1.33
    moil
    -1.30
    ierce
    -1.29
    BALL
    -1.25
    POSITIVE LOGITS
    �
    1.38
    ���
    1.30
     sentences
    1.28
     anecdotes
    1.27
     testimonies
    1.26
     Detective
    1.25
     investigative
    1.23
    Dialogue
    1.23
     Investigative
    1.22
     confidentiality
    1.22
    Activations Density 0.002%

    No Known Activations