© 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. 9169
    Prev
    Next
    INDEX
    Explanations

    references to factors affecting social or political dynamics

    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
    0:0.02
    1:0.09
    2:0.17
    3:0.08
    4:0.02
    5:0.03
    6:0.17
    7:0.06
    8:0.08
    9:0.07
    10:0.05
    11:0.11
    Negative Logits
    ahime
    -1.29
    alse
    -1.17
    edia
    -1.11
     someday
    -1.07
    ixel
    -1.03
    agram
    -0.97
    �
    -0.96
    ettle
    -0.93
    ello
    -0.93
    ICK
    -0.92
    POSITIVE LOGITS
     except
    1.47
    except
    1.39
    theless
    1.15
    together
    1.08
     toget
    1.01
    cape
    1.01
     forgiven
    1.00
     vo
    0.96
    WAYS
    0.93
    oglu
    0.93
    Activations Density 0.034%

    No Known Activations