INDEX

Explanations

phrases indicating the ability or capacity to perform an action

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

 CreateTagHelper

-1.06

تقاوى

-1.01

GEBURTSDATUM

-0.98

 Paglinawan

-0.93

 ***!

-0.91

ValueStyle

-0.89

TagMode

-0.88

NameInMap

-0.87

Попис

-0.87

 дописавши

-0.85

POSITIVE LOGITS

can

1.10

Can

0.96

Can

0.94

can

0.86

 able

0.83

 could

0.78

CAN

0.74

 сможет

0.70

 dapat

0.70

 können

0.66

Activations Density 0.098%

phrases indicating the ability or capacity to perform an action

No Comments

No Known Activations