© 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. 3-ATT-KK
    11. 5949
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate significant actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.10
    2:0.11
    3:0.03
    4:0.02
    5:0.04
    6:0.11
    7:0.11
    8:0.12
    9:0.09
    10:0.05
    11:0.13
    Negative Logits
    Kings
    -1.33
     Camden
    -1.31
    Magn
    -1.29
     Hok
    -1.27
    father
    -1.23
    brother
    -1.19
     Alexandria
    -1.19
    rehens
    -1.18
     Augustus
    -1.17
     Gothic
    -1.17
    POSITIVE LOGITS
     anymore
    1.98
    Downloadha
    1.70
     anybody
    1.67
     nor
    1.63
    plete
    1.61
    necess
    1.50
    hyde
    1.42
     anyone
    1.40
     any
    1.39
     slightest
    1.38
    Activations Density 0.026%

    No Known Activations