Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 27542
    Prev
    Next
    INDEX
    Explanations

    expressions indicating completion or status updates of actions

    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
    0:0.03
    1:0.02
    2:0.20
    3:0.09
    4:0.14
    5:0.04
    6:0.14
    7:0.09
    8:0.04
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     Cosponsors
    -1.61
    pring
    -1.43
    inline
    -1.36
     Winged
    -1.27
    eed
    -1.24
    catentry
    -1.22
    campus
    -1.20
    estic
    -1.18
     earliest
    -1.17
    istar
    -1.17
    POSITIVE LOGITS
    })
    1.43
     Virtue
    1.26
    ]}
    1.25
    ECK
    1.24
     Mahjong
    1.22
    �
    1.18
     Vegas
    1.18
    >)
    1.16
    ])
    1.16
     Herz
    1.16
    Activations Density 0.001%

    No Known Activations