© 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. 2-ATT-KK
    11. 21563
    Prev
    Next
    INDEX
    Explanations

    references to various fantasy worlds and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.19
    3:0.05
    4:0.16
    5:0.06
    6:0.02
    7:0.04
    8:0.05
    9:0.19
    10:0.07
    11:0.03
    Negative Logits
     actionGroup
    -1.41
    cknowled
    -1.39
     CPI
    -1.36
    forth
    -1.35
    TPS
    -1.31
     administrative
    -1.26
    keye
    -1.26
     administr
    -1.25
    etooth
    -1.22
    onew
    -1.19
    POSITIVE LOGITS
     fantasy
    1.71
     fantasies
    1.51
     immortality
    1.49
     sorcery
    1.45
     Fantasy
    1.44
     Horror
    1.40
    glers
    1.38
     dystop
    1.38
     realism
    1.37
    iuses
    1.37
    Activations Density 0.011%

    No Known Activations