© 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. 4773
    Prev
    Next
    INDEX
    Explanations

    negations and modifiers related to conditions or situations

    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
    0:0.03
    1:0.40
    2:0.03
    3:0.15
    4:0.03
    5:0.06
    6:0.06
    7:0.04
    8:0.03
    9:0.04
    10:0.07
    11:0.03
    Negative Logits
     particular
    -2.39
     warranted
    -2.33
     rightful
    -2.28
     proper
    -2.25
     illegitimate
    -2.24
     needed
    -2.17
     plag
    -2.03
     unquestion
    -2.02
     Investigations
    -2.00
     Zur
    -1.99
    POSITIVE LOGITS
     40
    4.36
     30
    4.29
     50
    4.09
     80
    3.90
     25
    3.72
     60
    3.72
     20
    3.67
     35
    3.65
     45
    3.56
     100
    3.53
    Activations Density 0.052%

    No Known Activations