© 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. 5-ATT-KK
    11. 41071
    Prev
    Next
    INDEX
    Explanations

    information related to conversations and statements made by individuals, highlighting dialogue and communication

    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
    0:0.08
    1:0.04
    2:0.04
    3:0.10
    4:0.03
    5:0.10
    6:0.02
    7:0.02
    8:0.08
    9:0.17
    10:0.12
    11:0.15
    Negative Logits
    bear
    -1.10
    ァ
    -1.10
     obscure
    -1.09
     Satanic
    -1.07
     iss
    -1.07
     fucking
    -1.06
     ().
    -1.03
     bastard
    -1.01
     Aram
    -1.01
     Elias
    -0.99
    POSITIVE LOGITS
    ebus
    1.45
    vironment
    1.14
    glers
    1.14
    Adds
    1.07
     anecd
    1.05
    hops
    1.05
    haw
    1.04
    "}],"
    0.99
    LU
    0.98
     Architects
    0.98
    Activations Density 0.484%

    No Known Activations