© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6518
    Prev
    Next
    INDEX
    Explanations

    instances of claims or assertions and their surrounding context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.10
    3:0.33
    4:0.02
    5:0.08
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.18
    11:0.02
    Negative Logits
    ��
    -2.76
    tops
    -2.30
    代
    -2.16
     effortlessly
    -2.10
    tackle
    -2.05
     pioneered
    -2.05
    xe
    -2.02
    izont
    -1.98
     transformed
    -1.96
    ottest
    -1.94
    POSITIVE LOGITS
     disagreements
    3.52
     irregularities
    3.51
     confidentiality
    3.20
     deficiencies
    3.14
     objections
    3.13
     grievances
    3.12
     complications
    3.10
     disagreement
    3.08
     concerns
    3.07
     delays
    3.00
    Activations Density 0.268%

    No Known Activations