© 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. 43950
    Prev
    Next
    INDEX
    Explanations

    transitions between scenes or events in a narrative, particularly those marked by time or location changes

    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
    0:0.18
    1:0.08
    2:0.07
    3:0.07
    4:0.03
    5:0.07
    6:0.05
    7:0.02
    8:0.06
    9:0.11
    10:0.11
    11:0.08
    Negative Logits
     immunity
    -1.36
     hatch
    -1.30
     Planes
    -1.28
     minim
    -1.26
     conflic
    -1.25
     disclaimer
    -1.24
     rept
    -1.21
     polyg
    -1.20
     regress
    -1.19
    externalActionCode
    -1.19
    POSITIVE LOGITS
    0200
    1.70
    �
    1.58
    >[
    1.56
    617
    1.53
     07
    1.48
    ticket
    1.47
     09
    1.46
    855
    1.42
    upt
    1.42
    ueller
    1.42
    Activations Density 0.004%

    No Known Activations