© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22925
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions indicative of strong emotions or states of being

    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
    0:0.08
    1:0.04
    2:0.18
    3:0.13
    4:0.08
    5:0.09
    6:0.06
    7:0.03
    8:0.06
    9:0.09
    10:0.09
    11:0.03
    Negative Logits
    闘
    -1.23
    ().
    -1.17
    thood
    -1.10
     RTX
    -1.09
    umbnail
    -1.08
    (),
    -1.08
    ERE
    -1.04
    udi
    -1.02
    acted
    -1.01
     helm
    -1.01
    POSITIVE LOGITS
     Beir
    1.31
    achev
    1.09
    ERG
    1.08
     Protocol
    1.07
     downhill
    1.07
    htaking
    1.06
     uphill
    1.05
     coincidence
    1.04
    yss
    1.01
     beh
    1.00
    Activations Density 0.043%

    No Known Activations