© 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. 42910
    Prev
    Next
    INDEX
    Explanations

    specific parts of a technical document or listing format

    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
    0:0.21
    1:0.24
    2:0.02
    3:0.03
    4:0.01
    5:0.16
    6:0.02
    7:0.01
    8:0.12
    9:0.07
    10:0.02
    11:0.02
    Negative Logits
    >[
    -2.14
    aca
    -2.04
    agen
    -2.00
    emption
    -1.96
    =~=~
    -1.94
    @#&
    -1.83
    ファ
    -1.83
    aiman
    -1.81
    escription
    -1.78
    advertising
    -1.75
    POSITIVE LOGITS
    redo
    1.78
     totality
    1.69
     hurry
    1.56
    paces
    1.53
     Participant
    1.51
     mark
    1.50
     crow
    1.49
     comma
    1.43
     stret
    1.38
     shuffle
    1.37
    Activations Density 0.312%

    No Known Activations