© 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. 44605
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or identifiers related to astronomical objects or phenomena

    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
    0:0.03
    1:0.02
    2:0.14
    3:0.07
    4:0.06
    5:0.04
    6:0.09
    7:0.19
    8:0.05
    9:0.04
    10:0.18
    11:0.05
    Negative Logits
     persuasion
    -1.85
     handic
    -1.85
     disgu
    -1.83
     inconvenience
    -1.81
     holster
    -1.63
     educate
    -1.59
     Pacers
    -1.58
     stall
    -1.58
     gloves
    -1.56
     wheelchair
    -1.55
    POSITIVE LOGITS
     orbiting
    1.90
    nan
    1.89
     orbits
    1.80
    axies
    1.77
     ⓘ
    1.74
     srfAttach
    1.71
    ��
    1.68
    oplan
    1.63
    avorite
    1.59
    uclear
    1.57
    Activations Density 0.001%

    No Known Activations