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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10459
    Prev
    Next
    INDEX
    Explanations

    confidence in the public sector compared to the private sector

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.09
    2:0.05
    3:0.05
    4:0.05
    5:0.05
    6:0.20
    7:0.02
    8:0.02
    9:0.28
    10:0.02
    11:0.08
    Negative Logits
    KI
    -3.53
     Axe
    -3.46
     Laz
    -3.43
    Legend
    -3.40
     Atkins
    -3.38
     Bass
    -3.38
     Juice
    -3.30
     Gear
    -3.25
     coils
    -3.21
     Bannon
    -3.19
    POSITIVE LOGITS
    public
    5.22
     Public
    5.20
     PUBLIC
    4.99
     public
    4.98
    ublic
    4.92
    BLIC
    4.86
    Public
    4.83
     privat
    3.77
     PR
    3.73
     privatization
    3.67
    Activations Density 0.015%

    No Known Activations