© 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. 43092
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, likely a person of authority or significance

    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
    0:0.06
    1:0.06
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.08
    8:0.07
    9:0.09
    10:0.10
    11:0.07
    Negative Logits
    ゴン
    -1.68
    nova
    -1.49
    osphere
    -1.47
    �
    -1.46
    agnar
    -1.42
    odox
    -1.36
    ��
    -1.35
    く
    -1.34
     Patriot
    -1.32
    enter
    -1.31
    POSITIVE LOGITS
     FIG
    1.57
     contingent
    1.55
    geries
    1.53
     gri
    1.48
    ğ
    1.47
     coping
    1.46
     cooperating
    1.45
     bragging
    1.44
     phased
    1.43
     consist
    1.35
    Activations Density 0.000%

    No Known Activations