© 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. 21826
    Prev
    Next
    INDEX
    Explanations

    proper nouns and certain brand names

    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
    1:0.02
    2:0.33
    3:0.12
    4:0.11
    5:0.05
    6:0.02
    7:0.02
    8:0.06
    9:0.09
    10:0.05
    11:0.02
    Negative Logits
    ��
    -2.05
     STATS
    -1.34
    OME
    -1.13
     metic
    -1.10
     Lanka
    -1.09
     Cobra
    -1.07
     Commando
    -1.07
    warts
    -1.06
     Edgar
    -1.06
    JJ
    -1.05
    POSITIVE LOGITS
    oshenko
    1.60
    sels
    1.56
    court
    1.41
    inas
    1.32
    γ
    1.26
    reck
    1.20
    uter
    1.18
    cell
    1.18
    henko
    1.17
    chen
    1.16
    Activations Density 0.007%

    No Known Activations