© 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. 3-ATT-KK
    11. 6533
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss concepts of legitimacy or legality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.07
    4:0.02
    5:0.03
    6:0.08
    7:0.13
    8:0.05
    9:0.03
    10:0.06
    11:0.35
    Negative Logits
    ��
    -1.42
    ctic
    -1.36
     overload
    -1.31
     exhaustion
    -1.29
    ched
    -1.24
    jit
    -1.22
    severe
    -1.21
    aten
    -1.19
     helicop
    -1.18
    intensive
    -1.16
    POSITIVE LOGITS
    Reviewer
    1.36
    �
    1.34
    ARR
    1.32
    AAA
    1.31
    soType
    1.27
    FN
    1.20
    OPLE
    1.20
    RF
    1.18
    xxxxxxxx
    1.15
    SpaceEngineers
    1.15
    Activations Density 0.022%

    No Known Activations