INDEX

Explanations

the word "apparently" in various contexts

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

 المعيارى

-0.60

 τί

-0.58

autique

-0.57

 Tinker

-0.56

ఞ

-0.55

lück

-0.55

ichern

-0.54

 exception

-0.54

toastr

-0.53

 становника

-0.53

POSITIVE LOGITS

 apparently

2.92

 allegedly

2.82

apparently

2.80

 supposedly

2.65

 Apparently

2.62

Apparently

2.56

 reportedly

2.55

 supuestamente

2.29

 aparentemente

2.16

 ostensibly

1.94

Activations Density 0.225%

the word "apparently" in various contexts

No Comments

No Known Activations