Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43384
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a call to action or direction, particularly related to watching or accessing content

    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
    0:0.02
    1:0.02
    2:0.11
    3:0.07
    4:0.06
    5:0.02
    6:0.16
    7:0.14
    8:0.03
    9:0.04
    10:0.11
    11:0.15
    Negative Logits
    heim
    -1.33
     Saga
    -1.28
     Cutter
    -1.23
     Fior
    -1.22
    arth
    -1.22
     Gard
    -1.21
    vironments
    -1.18
     Pist
    -1.18
     Harding
    -1.17
    facts
    -1.16
    POSITIVE LOGITS
     fuse
    1.50
    bley
    1.25
    igue
    1.22
     recycle
    1.17
     ILCS
    1.17
     charism
    1.15
     usb
    1.14
     Refresh
    1.14
     compe
    1.14
    nergy
    1.14
    Activations Density 0.005%

    No Known Activations