© 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. 12943
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and contradictions

    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
    0:0.05
    1:0.02
    2:0.19
    3:0.04
    4:0.05
    5:0.05
    6:0.03
    7:0.08
    8:0.17
    9:0.03
    10:0.15
    11:0.08
    Negative Logits
    held
    -1.19
    wayne
    -1.16
    renheit
    -1.14
    quel
    -1.13
    hovah
    -1.10
     Locations
    -1.10
    ��
    -1.10
     Survivors
    -1.08
    riter
    -1.05
    ctors
    -1.04
    POSITIVE LOGITS
     quite
    1.09
     adequately
    1.08
     incorpor
    1.02
     institutional
    0.99
    ּ
    0.98
     last
    0.97
     sufficiently
    0.96
     aloud
    0.95
     apartheid
    0.95
     fit
    0.94
    Activations Density 0.078%

    No Known Activations