© 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. 44020
    Prev
    Next
    INDEX
    Explanations

    instances of structured annotations or references in the text

    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
    0:0.15
    1:0.19
    2:0.06
    3:0.04
    4:0.03
    5:0.15
    6:0.06
    7:0.02
    8:0.10
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
    veh
    -2.07
     mans
    -1.67
    car
    -1.65
     Canal
    -1.61
    wagen
    -1.60
    vict
    -1.60
    issance
    -1.58
    tor
    -1.56
    rium
    -1.55
    mir
    -1.53
    POSITIVE LOGITS
    Updated
    2.76
     Updated
    2.62
    PDATED
    2.30
    Posted
    2.29
    updated
    2.26
     updated
    2.15
    Published
    2.08
    ��
    2.07
    ��
    2.06
     Accessed
    2.02
    Activations Density 0.000%

    No Known Activations