© 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. 38255
    Prev
    Next
    INDEX
    Explanations

    terms related to capability and empowerment

    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
    0:0.11
    1:0.25
    2:0.04
    3:0.04
    4:0.04
    5:0.17
    6:0.05
    7:0.04
    8:0.06
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
     ¶
    -2.02
     ®
    -1.86
     Ack
    -1.79
    û
    -1.71
    ¶
    -1.64
     Browne
    -1.60
    ô
    -1.56
    atives
    -1.56
    paragraph
    -1.56
    pac
    -1.53
    POSITIVE LOGITS
    Ability
    2.09
    ��
    1.81
     able
    1.74
     Forced
    1.59
     disse
    1.58
     react
    1.57
     synchronized
    1.56
     dism
    1.52
     epile
    1.50
    Enhanced
    1.48
    Activations Density 0.004%

    No Known Activations