INDEX

Explanations

references to sports events and player performances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

winning and losing

np_acts-logits-general · gemini-2.0-flash

win or lose

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

徊

-0.70

 CreateTagHelper

-0.67

+#+#

-0.65

 Савезне

-0.63

IsMutable

-0.62

 Roskov

-0.61

sidemargin

-0.60

IndentedString

-0.60

躇

-0.60

DrawerToggle

-0.59

POSITIVE LOGITS

 defeat

0.83

 victory

0.76

 defeated

0.75

 defeating

0.66

 triunfo

0.64

 gewinnt

0.62

 score

0.59

 victorious

0.58

win

0.58

 defeats

0.57

Activations Density 0.183%

references to sports events and player performances

winning and losing

win or lose

No Comments

No Known Activations