© 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. 2-ATT-KK
    11. 16088
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone establishing themselves in a particular role or position

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.16
    3:0.05
    4:0.28
    5:0.04
    6:0.02
    7:0.01
    8:0.22
    9:0.08
    10:0.04
    11:0.01
    Negative Logits
    bl
    -1.46
    groupon
    -1.33
    worker
    -1.32
    abus
    -1.32
    washing
    -1.30
     spills
    -1.30
    workers
    -1.30
    bowl
    -1.28
    wrap
    -1.25
    wid
    -1.24
    POSITIVE LOGITS
    OPLE
    1.69
     Anon
    1.43
    -+-+
    1.38
     residency
    1.38
    ITNESS
    1.37
    uberty
    1.36
    ADRA
    1.34
     Presence
    1.34
    agy
    1.33
     Amend
    1.31
    Activations Density 0.009%

    No Known Activations