© 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. 2-ATT-KK
    11. 22166
    Prev
    Next
    INDEX
    Explanations

    locations and proximity references in the text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.10
    1:0.02
    2:0.09
    3:0.10
    4:0.02
    5:0.11
    6:0.04
    7:0.07
    8:0.15
    9:0.06
    10:0.11
    11:0.06
    Negative Logits
     adaptation
    -1.10
     Niet
    -1.06
     POV
    -1.06
     rewriting
    -1.03
     subtitles
    -1.01
     Weird
    -1.00
     Spock
    -1.00
     adapt
    -0.99
     Canaver
    -0.98
     behav
    -0.98
    POSITIVE LOGITS
    avia
    1.28
    arma
    1.28
    una
    1.23
    waters
    1.23
    sun
    1.21
    istar
    1.20
    union
    1.19
    ropolis
    1.19
    init
    1.18
    hess
    1.17
    Activations Density 0.039%

    No Known Activations