© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29055
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong personal opinions or assessments

    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
    0:0.03
    1:0.02
    2:0.11
    3:0.08
    4:0.12
    5:0.04
    6:0.05
    7:0.19
    8:0.05
    9:0.05
    10:0.09
    11:0.12
    Negative Logits
    jri
    -1.86
     berth
    -1.49
     minors
    -1.46
     manslaughter
    -1.43
     detain
    -1.40
     liability
    -1.40
    wait
    -1.37
     imprison
    -1.36
    ISA
    -1.35
     airline
    -1.35
    POSITIVE LOGITS
     Lists
    1.62
    geist
    1.58
    iety
    1.45
    oute
    1.39
     Archive
    1.38
     Heritage
    1.35
     Explosive
    1.34
     Digest
    1.32
    ographer
    1.30
     Percent
    1.30
    Activations Density 0.000%

    No Known Activations