© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 45480
    Prev
    Next
    INDEX
    Explanations

    CSS styles and layout properties related to positioning and transformation

    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
    0:0.04
    1:0.04
    2:0.12
    3:0.08
    4:0.06
    5:0.08
    6:0.12
    7:0.14
    8:0.06
    9:0.06
    10:0.05
    11:0.11
    Negative Logits
     Sprite
    -1.53
     rall
    -1.36
     uniqueness
    -1.34
     bottled
    -1.33
    dom
    -1.28
     specialty
    -1.25
    ramid
    -1.24
    ulnerable
    -1.24
     cele
    -1.24
     accessibility
    -1.23
    POSITIVE LOGITS
    ���
    1.71
    ormon
    1.56
    �
    1.55
    CLASSIFIED
    1.55
     contrary
    1.53
    76561
    1.44
    ecd
    1.44
    >:
    1.43
    ende
    1.37
     Emails
    1.33
    Activations Density 0.001%

    No Known Activations