© 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. 10-ATT-KK
    11. 7764
    Prev
    Next
    INDEX
    Explanations

    occurrences of high-frequency or common nouns and verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.02
    3:0.03
    4:0.04
    5:0.07
    6:0.03
    7:0.03
    8:0.02
    9:0.17
    10:0.03
    11:0.44
    Negative Logits
     surroundings
    -2.66
     realities
    -2.63
    reality
    -2.32
     Situation
    -2.22
    Vision
    -2.19
     environments
    -2.17
    speak
    -2.14
    imens
    -2.13
     existence
    -2.13
    Experience
    -2.13
    POSITIVE LOGITS
     strings
    2.67
    strings
    2.55
     buttons
    2.46
     hooks
    2.37
     bonuses
    2.32
    strap
    2.32
     stunt
    2.30
     teeth
    2.28
     brake
    2.25
     button
    2.25
    Activations Density 0.014%

    No Known Activations