© 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. 39681
    Prev
    Next
    INDEX
    Explanations

    expressions related to subscribing to newsletters or getting updates

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.01
    1:0.00
    2:0.22
    3:0.19
    4:0.04
    5:0.02
    6:0.08
    7:0.06
    8:0.06
    9:0.05
    10:0.10
    11:0.10
    Negative Logits
    ère
    -1.41
    ENC
    -1.35
     Rapp
    -1.33
     Cooke
    -1.32
     Franç
    -1.30
     Spiel
    -1.30
     Ecology
    -1.30
     obscurity
    -1.27
    cott
    -1.24
    ENCE
    -1.22
    POSITIVE LOGITS
    btn
    1.31
     widgets
    1.30
    ]}
    1.30
     interact
    1.24
     selves
    1.24
    azy
    1.23
    farious
    1.21
     tick
    1.21
    hetic
    1.20
    cha
    1.20
    Activations Density 0.001%

    No Known Activations