© 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. 5-ATT-KK
    11. 45892
    Prev
    Next
    INDEX
    Explanations

    negations and limitations in various statements

    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
    0:0.01
    1:0.02
    2:0.17
    3:0.10
    4:0.09
    5:0.02
    6:0.24
    7:0.05
    8:0.05
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
    akov
    -1.49
    oons
    -1.35
    MENTS
    -1.34
    DAQ
    -1.30
    ews
    -1.27
    ials
    -1.27
    ungle
    -1.21
    bors
    -1.19
    adders
    -1.18
    Hero
    -1.17
    POSITIVE LOGITS
     Ramos
    1.37
     haunt
    1.31
     Pwr
    1.30
     elector
    1.22
     anat
    1.19
    ��
    1.17
     Rouse
    1.16
     fracture
    1.15
     convergence
    1.13
     theoret
    1.11
    Activations Density 0.048%

    No Known Activations