© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 12090
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions about particular situations or actions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.14
    3:0.09
    4:0.04
    5:0.11
    6:0.04
    7:0.05
    8:0.10
    9:0.10
    10:0.10
    11:0.05
    Negative Logits
    Target
    -0.93
    anchester
    -0.89
    Stage
    -0.85
     Yuan
    -0.84
     Liga
    -0.83
     Category
    -0.82
    DX
    -0.81
    Track
    -0.81
    Blade
    -0.80
    nih
    -0.80
    POSITIVE LOGITS
     alike
    1.31
     conclud
    1.30
     accordingly
    1.12
     consequently
    1.09
    osponsors
    1.07
     thereof
    1.06
     proport
    1.05
     importantly
    1.04
    entious
    1.03
     respectively
    1.03
    Activations Density 0.361%

    No Known Activations