© 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. 21741
    Prev
    Next
    INDEX
    Explanations

    mentions of family and friends

    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
    0:0.05
    1:0.04
    2:0.14
    3:0.06
    4:0.21
    5:0.10
    6:0.03
    7:0.04
    8:0.05
    9:0.10
    10:0.08
    11:0.04
    Negative Logits
    ording
    -1.36
    ftime
    -1.33
     timed
    -1.26
    tained
    -1.26
    EC
    -1.24
    IM
    -1.24
    INAL
    -1.24
    UC
    -1.24
     Hail
    -1.22
     Contra
    -1.21
    POSITIVE LOGITS
     alike
    1.78
     strugg
    1.52
    mates
    1.51
     acquaintances
    1.50
     principals
    1.49
     traged
    1.46
    eteria
    1.44
     mosqu
    1.42
     kindred
    1.40
    itaire
    1.38
    Activations Density 0.006%

    No Known Activations