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. 9-ATT-KK
    6. 20639
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, organizations, and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.07
    3:0.20
    4:0.02
    5:0.04
    6:0.02
    7:0.04
    8:0.03
    9:0.03
    10:0.39
    11:0.02
    Negative Logits
    tom
    -2.23
     Rai
    -2.11
     elsewhere
    -2.07
     Gork
    -1.98
    hao
    -1.89
    Gameplay
    -1.75
     nods
    -1.75
    gran
    -1.74
     Yose
    -1.72
     RTX
    -1.71
    POSITIVE LOGITS
    )))
    2.77
    ))))
    2.64
    )).
    2.58
    >)
    2.57
    )),
    2.57
    ]).
    2.43
     )]
    2.39
    ]),
    2.33
    thood
    2.25
     expect
    2.21
    Activations Density 0.029%

    No Known Activations