© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 19699
    Prev
    Next
    INDEX
    Explanations

    references to "acts" in a negative or significant context

    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
    0:0.01
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.02
    6:0.23
    7:0.36
    8:0.02
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     sinks
    -1.34
    emies
    -1.34
    isSpecialOrderable
    -1.33
    ilts
    -1.33
     "$:/
    -1.31
    tops
    -1.30
    illac
    -1.28
     doubts
    -1.28
    aments
    -1.22
    answered
    -1.22
    POSITIVE LOGITS
     omission
    1.70
     reconciliation
    1.58
     prevention
    1.47
     Compliance
    1.36
    BAT
    1.34
    ropri
    1.33
    rave
    1.31
    WA
    1.31
    ヘ
    1.31
     liaison
    1.30
    Activations Density 0.007%

    No Known Activations