© 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. 46760
    Prev
    Next
    INDEX
    Explanations

    references to stories and narratives involving notable events or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.01
    2:0.13
    3:0.04
    4:0.07
    5:0.03
    6:0.47
    7:0.02
    8:0.02
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
     oneself
    -1.55
    龍�
    -1.46
    ankind
    -1.42
    龍契士
    -1.36
    someone
    -1.31
    alach
    -1.30
     regul
    -1.26
    ICLE
    -1.20
    田
    -1.20
    女
    -1.19
    POSITIVE LOGITS
     Revenge
    1.41
     Corner
    1.26
     CLSID
    1.22
     Twisted
    1.17
    maxwell
    1.14
     Success
    1.13
    igue
    1.11
    phan
    1.11
     ff
    1.08
    agents
    1.08
    Activations Density 0.099%

    No Known Activations