© 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. 9-ATT-KK
    11. 16305
    Prev
    Next
    INDEX
    Explanations

    phrases related to information and guidance on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.24
    7:0.03
    8:0.11
    9:0.18
    10:0.04
    11:0.05
    Negative Logits
     Cabin
    -3.98
     Alley
    -3.96
     Hawk
    -3.95
    hyde
    -3.92
     Bengals
    -3.86
     Kem
    -3.85
    oglu
    -3.80
    Connector
    -3.76
     Chow
    -3.70
     Eld
    -3.69
    POSITIVE LOGITS
     NS
    10.71
    NS
    9.25
     ns
    5.47
     NSW
    5.30
    NP
    5.04
    ns
    4.97
     NP
    4.89
     AS
    4.13
     NRS
    4.04
     Nek
    4.01
    Activations Density 0.002%

    No Known Activations