© 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. 43104
    Prev
    Next
    INDEX
    Explanations

    references to tangible objects or items

    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
    0:0.08
    1:0.11
    2:0.09
    3:0.08
    4:0.08
    5:0.07
    6:0.09
    7:0.07
    8:0.07
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    ゴン
    -1.99
    ingo
    -1.97
    ogl
    -1.87
    ionic
    -1.85
    inian
    -1.77
    ーティ
    -1.76
    speech
    -1.68
    ocrin
    -1.67
    externalActionCode
    -1.63
     Lunch
    -1.62
    POSITIVE LOGITS
     advancements
    1.59
     Effective
    1.55
    forth
    1.52
     quant
    1.51
     advancement
    1.49
     reproduction
    1.48
     regained
    1.48
     weaker
    1.46
     repeal
    1.46
     DEFENSE
    1.44
    Activations Density 0.000%

    No Known Activations