© 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. 47056
    Prev
    Next
    INDEX
    Explanations

    references to reflections or thoughts on various subjects

    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
    1:0.01
    2:0.06
    3:0.09
    4:0.19
    5:0.02
    6:0.04
    7:0.31
    8:0.04
    9:0.03
    10:0.06
    11:0.07
    Negative Logits
    shoot
    -1.48
    ausible
    -1.47
    esm
    -1.42
    mouth
    -1.42
    achable
    -1.37
    moderate
    -1.36
    azo
    -1.35
    resistant
    -1.34
    medium
    -1.33
    compatible
    -1.32
    POSITIVE LOGITS
     remem
    1.75
     realities
    1.69
     respons
    1.67
     history
    1.62
     clich
    1.56
     symbolism
    1.56
     memories
    1.55
     responsibilities
    1.51
     complexities
    1.51
     timeless
    1.50
    Activations Density 0.005%

    No Known Activations