© 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. 5-ATT-KK
    6. 35582
    Prev
    Next
    INDEX
    Explanations

    direct quotations or dialogue from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.02
    2:0.22
    3:0.10
    4:0.05
    5:0.06
    6:0.04
    7:0.06
    8:0.07
    9:0.10
    10:0.11
    11:0.09
    Negative Logits
     Luxem
    -1.35
     Ambro
    -1.34
     militar
    -1.30
     Ig
    -1.27
     Indy
    -1.23
     Kinect
    -1.21
     Ranger
    -1.21
     comprom
    -1.20
    Mesh
    -1.18
     Instrument
    -1.18
    POSITIVE LOGITS
    ��
    1.72
    edi
    1.49
    eye
    1.48
    ↵ 
    1.48
    ignty
    1.38
    ords
    1.37
    ramer
    1.36
    ording
    1.34
    aunders
    1.32
    said
    1.28
    Activations Density 0.023%

    No Known Activations