INDEX

Explanations

expressions of high praise or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

chism

-0.83

InputBorder

-0.77

skjaer

-0.74

RenderAtEndOf

-0.74

ReusableCell

-0.73

epiece

-0.73

 כן

-0.71

 ویکی‌پدیا

-0.70

hoea

-0.70

meteries

-0.67

POSITIVE LOGITS

 great

2.94

great

2.84

Great

2.61

GREAT

2.58

 Great

2.55

 GREAT

2.51

 wonderful

1.61

 greats

1.60

 tremendous

1.50

 terrific

1.48

Activations Density 0.048%

expressions of high praise or quality

No Comments

No Known Activations