© 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. 42889
    Prev
    Next
    INDEX
    Explanations

    quotations and dialogue 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
    0:0.06
    1:0.04
    2:0.24
    3:0.10
    4:0.05
    5:0.05
    6:0.04
    7:0.03
    8:0.08
    9:0.08
    10:0.10
    11:0.08
    Negative Logits
     worsening
    -1.55
    vous
    -1.53
     congestion
    -1.48
    cessive
    -1.44
     Trou
    -1.44
     warming
    -1.41
     speeding
    -1.41
     vengeance
    -1.40
     uncontroll
    -1.39
     undes
    -1.39
    POSITIVE LOGITS
    魔
    2.14
    Spec
    2.10
    Catalog
    2.05
    Manufact
    2.03
    Model
    1.98
    版
    1.98
    Works
    1.96
    TYPE
    1.91
    Weapons
    1.89
    Label
    1.84
    Activations Density 0.000%

    No Known Activations