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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22221
    Prev
    Next
    INDEX
    Explanations

    instances of physical confrontation and aggression

    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
    1:0.09
    2:0.04
    3:0.06
    4:0.03
    5:0.07
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.19
    11:0.08
    Negative Logits
    ahime
    -1.38
     shaping
    -1.33
     billionaires
    -1.33
     collaborations
    -1.32
     globally
    -1.29
    omics
    -1.27
     investing
    -1.27
     premier
    -1.26
     ambitious
    -1.25
    uably
    -1.25
    POSITIVE LOGITS
     incrim
    1.51
     appellant
    1.36
     ambul
    1.33
    Fax
    1.31
    gew
    1.30
     ambulance
    1.29
     mol
    1.28
     suspic
    1.26
    idav
    1.26
     nearby
    1.23
    Activations Density 0.520%

    No Known Activations