© 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. 39714
    Prev
    Next
    INDEX
    Explanations

    specific sports player information and related statistics

    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
    0:0.02
    1:0.02
    2:0.17
    3:0.13
    4:0.05
    5:0.04
    6:0.03
    7:0.03
    8:0.03
    9:0.05
    10:0.19
    11:0.18
    Negative Logits
     tc
    -1.42
    ワ
    -1.24
     colonies
    -1.23
    )?
    -1.17
     civilizations
    -1.14
     cosmos
    -1.14
     clich
    -1.13
     comma
    -1.12
     manuals
    -1.12
     rc
    -1.12
    POSITIVE LOGITS
    ected
    1.29
    )=(
    1.26
    isconsin
    1.23
    orget
    1.22
     Abdullah
    1.20
     illegally
    1.20
    ASHINGTON
    1.18
    WASHINGTON
    1.17
    igham
    1.17
    jad
    1.16
    Activations Density 0.149%

    No Known Activations