© 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 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. 27266
    Prev
    Next
    INDEX
    Explanations

    themes related to consequences, both positive and negative, 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
    1:0.02
    2:0.10
    3:0.17
    4:0.12
    5:0.04
    6:0.22
    7:0.07
    8:0.03
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    Rated
    -1.65
     Annotations
    -1.62
    fleet
    -1.56
    aido
    -1.44
     Nanto
    -1.41
    uyomi
    -1.35
    psey
    -1.34
    reply
    -1.33
     [+
    -1.31
     Rico
    -1.27
    POSITIVE LOGITS
     bang
    1.41
     ourselves
    1.36
     backward
    1.34
     democrat
    1.28
     perfection
    1.24
     essentials
    1.22
     apples
    1.22
     peripher
    1.21
     convenient
    1.19
     backwards
    1.19
    Activations Density 0.026%

    No Known Activations