© 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. 5-ATT-KK
    11. 43213
    Prev
    Next
    INDEX
    Explanations

    references to taking action or control in difficult situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.26
    3:0.07
    4:0.14
    5:0.02
    6:0.11
    7:0.13
    8:0.04
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    minster
    -1.46
     Flavoring
    -1.44
    anish
    -1.39
    expr
    -1.38
     captcha
    -1.36
    vious
    -1.35
    iston
    -1.35
     Frames
    -1.34
     graphs
    -1.32
     newsp
    -1.31
    POSITIVE LOGITS
     vengeance
    1.56
    venge
    1.47
     Moreno
    1.47
    hyde
    1.43
    umbn
    1.41
    uld
    1.40
    bered
    1.36
     favor
    1.33
    ��
    1.31
    ��
    1.30
    Activations Density 0.000%

    No Known Activations