© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21799
    Prev
    Next
    INDEX
    Explanations

    phrases related to restrictions and limitations

    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
    0:0.04
    1:0.03
    2:0.24
    3:0.07
    4:0.23
    5:0.03
    6:0.03
    7:0.03
    8:0.06
    9:0.11
    10:0.05
    11:0.02
    Negative Logits
    itia
    -1.67
    cill
    -1.59
    ellar
    -1.56
     conclud
    -1.41
    bleacher
    -1.36
     Dhabi
    -1.33
     skelet
    -1.33
    zona
    -1.32
    aris
    -1.32
    paren
    -1.31
    POSITIVE LOGITS
    stakes
    1.42
    isk
    1.27
    ocked
    1.25
    enged
    1.25
    ebin
    1.23
    龍契士
    1.22
    ousy
    1.21
    icky
    1.21
    awed
    1.18
    auga
    1.17
    Activations Density 0.001%

    No Known Activations