© 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. 2-ATT-KK
    11. 13604
    Prev
    Next
    INDEX
    Explanations

    specific events or actions described in a relatively complex manner

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.09
    3:0.10
    4:0.02
    5:0.05
    6:0.05
    7:0.09
    8:0.05
    9:0.15
    10:0.18
    11:0.09
    Negative Logits
    urnal
    -1.20
    tackle
    -1.13
     sidx
    -1.07
    volent
    -1.07
    throp
    -1.06
    thood
    -1.02
    azeera
    -1.01
    viron
    -1.01
    inas
    -1.01
    isine
    -1.01
    POSITIVE LOGITS
     itself
    1.49
    ACTED
    1.02
     determines
    1.01
     Swanson
    0.98
     McCartney
    0.98
     Adren
    0.97
     Gemini
    0.97
     Huntington
    0.94
     Hamm
    0.93
     Hubbard
    0.93
    Activations Density 0.401%

    No Known Activations