INDEX

Explanations

variations of the word "clear."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 &___

-0.90

didSet

-0.86

 للاسماء

-0.81

yntaxException

-0.78

+:+

-0.78

 ویکی‌پدیا

-0.78

fjspx

-0.76

 AssemblyProduct

-0.74

StoryboardSegue

-0.73

FTFY

-0.71

POSITIVE LOGITS

 clear

3.57

 Clear

3.50

Clear

3.47

clear

3.33

 CLEAR

3.09

CLEAR

2.79

 clears

2.72

 cleared

2.52

 Clears

2.49

 clearing

2.43

Activations Density 0.057%

variations of the word "clear."

No Comments

No Known Activations