© 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 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. 43414
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to structures or systems

    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
    1:0.03
    2:0.02
    3:0.02
    4:0.02
    5:0.52
    6:0.02
    7:0.01
    8:0.03
    9:0.14
    10:0.08
    11:0.03
    Negative Logits
     ILCS
    -1.33
    UFC
    -1.19
    IAS
    -1.18
    elta
    -1.17
     FS
    -1.17
    dfx
    -1.16
    essee
    -1.15
    planes
    -1.10
    lower
    -1.10
    ussian
    -1.08
    POSITIVE LOGITS
     Tid
    1.23
     Orche
    1.18
     tid
    1.16
     recy
    1.10
     resume
    1.07
    ゴン
    1.06
     equival
    1.04
     GOODMAN
    1.04
    swers
    1.03
    addle
    1.02
    Activations Density 2.597%

    No Known Activations