© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 10290
    Prev
    Next
    INDEX
    Explanations

    evidence related to scientific studies and their implications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.09
    4:0.04
    5:0.07
    6:0.02
    7:0.06
    8:0.06
    9:0.11
    10:0.25
    11:0.13
    Negative Logits
    fuck
    -1.22
    ニ
    -1.13
     Eater
    -1.12
     Kills
    -1.09
     HELL
    -1.07
    peace
    -1.06
     Carnage
    -1.05
    jack
    -1.05
    nah
    -1.05
    claw
    -1.03
    POSITIVE LOGITS
     methodological
    1.75
     analytical
    1.59
     empirical
    1.50
     analyses
    1.49
     anecdotal
    1.48
     biases
    1.46
     speculative
    1.42
     hypotheses
    1.40
     flawed
    1.39
     IPCC
    1.38
    Activations Density 0.954%

    No Known Activations