© 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. 3-ATT-KK
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    words related to rejection or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.11
    3:0.03
    4:0.06
    5:0.09
    6:0.06
    7:0.07
    8:0.04
    9:0.07
    10:0.18
    11:0.09
    Negative Logits
    ��
    -1.26
    natureconservancy
    -1.24
    ghai
    -1.21
    angular
    -1.20
    assic
    -1.15
     Orbit
    -1.12
     Milky
    -1.11
    ocene
    -1.10
     breeze
    -1.06
     tidal
    -1.06
    POSITIVE LOGITS
     unsuccessfully
    1.35
     unsub
    1.25
     repeatedly
    1.19
     angrily
    1.15
    Examples
    1.15
     citing
    1.13
     amnesty
    1.13
     falsely
    1.12
     apologize
    1.10
    claim
    1.07
    Activations Density 0.084%

    No Known Activations