© 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. 28046
    Prev
    Next
    INDEX
    Explanations

    dialogue interactions and character responses

    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
    0:0.14
    1:0.02
    2:0.08
    3:0.10
    4:0.10
    5:0.05
    6:0.05
    7:0.06
    8:0.07
    9:0.12
    10:0.07
    11:0.09
    Negative Logits
    conservancy
    -1.93
    DragonMagazine
    -1.84
    ️
    -1.67
    ™:
    -1.52
    `,
    -1.45
     elig
    -1.43
     experien
    -1.42
    externalActionCode
    -1.39
    ixel
    -1.39
    Downloadha
    -1.35
    POSITIVE LOGITS
     reply
    1.42
     replied
    1.39
    oward
    1.22
     exploded
    1.22
     explodes
    1.21
     Downs
    1.21
    acker
    1.19
     angrily
    1.18
     responds
    1.18
     Rap
    1.17
    Activations Density 0.009%

    No Known Activations