© 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. 9-ATT-KK
    11. 4957
    Prev
    Next
    INDEX
    Explanations

    negative constructions related to decision-making or obligations

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.15
    4:0.02
    5:0.05
    6:0.04
    7:0.07
    8:0.02
    9:0.05
    10:0.41
    11:0.05
    Negative Logits
     compared
    -1.93
     differed
    -1.90
     sidelines
    -1.89
     unnamed
    -1.88
     footnote
    -1.88
     uncertain
    -1.87
     absence
    -1.86
     contrasts
    -1.84
     unknown
    -1.83
     mere
    -1.83
    POSITIVE LOGITS
    *,
    2.21
     enough
    2.19
     ASAP
    2.17
     satisfactory
    2.11
    �
    2.04
     sufficiently
    1.97
    ®,
    1.90
    Ready
    1.89
     please
    1.87
    catentry
    1.87
    Activations Density 0.105%

    No Known Activations