Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13705
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "itself" being used emphatically

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.07
    1:0.03
    2:0.14
    3:0.12
    4:0.03
    5:0.14
    6:0.04
    7:0.03
    8:0.12
    9:0.13
    10:0.08
    11:0.03
    Negative Logits
    ADVERTISEMENT
    -1.12
    UFF
    -1.10
    )"
    -1.09
     prelim
    -1.09
    AMA
    -1.07
     condol
    -1.05
    龍�
    -1.04
    license
    -1.04
     advers
    -1.03
    VID
    -1.01
    POSITIVE LOGITS
    onto
    1.09
    stood
    1.09
     ±
    1.08
     Goose
    1.07
    hement
    1.07
    paced
    1.06
    ifax
    1.06
     Norris
    1.04
    raltar
    1.03
    accessible
    1.03
    Activations Density 0.059%

    No Known Activations