INDEX

Explanations

negative forms of the verb "to be"

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

was

-0.61

fcntl

-0.59

 Normdatei

-0.57

HasAnnotation

-0.57

SqlDataReader

-0.55

ItemGroup

-0.55

PropertyChanging

-0.55

was

-0.54

wasn

-0.54

awaiter

-0.54

POSITIVE LOGITS

are

2.04

are

1.90

ARE

1.89

Are

1.81

Are

1.78

 aren

1.68

 são

1.68

 were

1.64

 sind

1.64

 sont

1.60

Activations Density 0.412%

negative forms of the verb "to be"

No Comments

No Known Activations