INDEX

Explanations

phrases indicating purpose or intent, specifically the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

makeConstraints

-0.69

Vidite

-0.65

 surla

-0.65

CGRectMake

-0.62

 Misalnya

-0.62

Види

-0.61

InlineData

-0.61

ïa

-0.61

extAlignment

-0.60

')['

-0.58

POSITIVE LOGITS

to

0.81

 να

0.78

ที่จะ

0.78

To

0.73

To

0.72

 skall

0.70

să

0.66

TO

0.66

 чтобы

0.65

จะ

0.65

Activations Density 1.137%

phrases indicating purpose or intent, specifically the word "to."

No Comments

No Known Activations