© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative impacts or consequences

    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
    1:0.01
    2:0.08
    3:0.07
    4:0.14
    5:0.04
    6:0.05
    7:0.30
    8:0.04
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
    grounds
    -1.58
    Esc
    -1.35
    ife
    -1.35
    thing
    -1.34
     opin
    -1.34
    soDeliveryDate
    -1.32
    itbart
    -1.32
     gist
    -1.29
    adder
    -1.29
     estab
    -1.28
    POSITIVE LOGITS
    bill
    1.66
     iceberg
    1.50
     Overs
    1.49
    ��
    1.44
     subsidies
    1.42
    lyak
    1.42
    ドラ
    1.38
     budgetary
    1.36
     allocations
    1.33
     disproportionately
    1.32
    Activations Density 0.003%

    No Known Activations