© 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. 5-ATT-KK
    11. 43708
    Prev
    Next
    INDEX
    Explanations

    negative statements and expressions of doubt or refusal

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.21
    2:0.04
    3:0.05
    4:0.02
    5:0.13
    6:0.04
    7:0.03
    8:0.12
    9:0.07
    10:0.04
    11:0.07
    Negative Logits
     Monthly
    -1.39
     ¶
    -1.31
    yip
    -1.30
    Ra
    -1.28
    >[
    -1.27
    resents
    -1.26
    Hig
    -1.25
    nesday
    -1.25
    ↑
    -1.23
     circled
    -1.22
    POSITIVE LOGITS
    pload
    1.78
    �
    1.56
    ��
    1.56
    bish
    1.54
     autos
    1.53
    ���
    1.51
    ufact
    1.50
    artment
    1.49
    okia
    1.47
    ulp
    1.45
    Activations Density 0.061%

    No Known Activations