© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3637
    Prev
    Next
    INDEX
    Explanations

    verbs associated with actions and processes related to creation, governance, and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.02
    2:0.13
    3:0.11
    4:0.17
    5:0.03
    6:0.13
    7:0.12
    8:0.03
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
     apologies
    -1.49
     consolation
    -1.40
     hypoc
    -1.38
     regrets
    -1.38
     horr
    -1.35
     blaming
    -1.35
     regret
    -1.35
     ashes
    -1.33
     hating
    -1.33
     whining
    -1.33
    POSITIVE LOGITS
    agascar
    1.50
    uate
    1.41
    burse
    1.39
    ropolis
    1.38
    ])
    1.31
    ctic
    1.30
    OTAL
    1.27
    ructure
    1.26
    igible
    1.23
    ]);
    1.21
    Activations Density 0.032%

    No Known Activations