© 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. 40331
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic publishing challenges and citation metrics

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.10
    4:0.05
    5:0.07
    6:0.03
    7:0.05
    8:0.06
    9:0.08
    10:0.22
    11:0.17
    Negative Logits
     Farage
    -1.28
     symbolism
    -1.25
    chet
    -1.24
     flashback
    -1.19
     catchy
    -1.17
     narration
    -1.17
     prophecy
    -1.15
     Hanna
    -1.15
    translation
    -1.14
    itsch
    -1.12
    POSITIVE LOGITS
    Cop
    1.33
     forfe
    1.30
     ineligible
    1.28
     submitting
    1.26
     elig
    1.25
     withdrawing
    1.23
     vic
    1.23
     Colo
    1.17
     withdrawn
    1.17
    brance
    1.16
    Activations Density 0.018%

    No Known Activations