© 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. 5-ATT-KK
    11. 43596
    Prev
    Next
    INDEX
    Explanations

    instances of the word "here" related to citations or links

    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
    0:0.16
    1:0.05
    2:0.11
    3:0.05
    4:0.08
    5:0.05
    6:0.07
    7:0.03
    8:0.15
    9:0.04
    10:0.05
    11:0.10
    Negative Logits
    ディ
    -1.65
    WARE
    -1.44
    cible
    -1.36
     thrott
    -1.36
    ヘ
    -1.32
    rotein
    -1.32
    ocking
    -1.28
     prox
    -1.27
    м
    -1.27
     decomp
    -1.26
    POSITIVE LOGITS
     CrossRef
    1.58
    lace
    1.40
    morrow
    1.38
     respectively
    1.37
     Peg
    1.36
    姫
    1.36
    bey
    1.35
    !.
    1.35
     Clicker
    1.34
     Scrib
    1.31
    Activations Density 0.001%

    No Known Activations