INDEX

Explanations

phrases indicating uncertainty or conditions related to certain situations or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ahuila

-0.56

 lahat

-0.56

 AppCompatTheme

-0.49

 EQUAL

-0.49

 ObjectMapper

-0.48

 maroc

-0.46

setVerticalGroup

-0.46

 AttributeSet

-0.46

 taba

-0.45

ėte

-0.45

POSITIVE LOGITS

 particular

0.82

 something

0.82

 some

0.82

 somethin

0.81

某

0.79

 jakiś

0.78

 通販

0.75

떤

0.75

something

0.75

 qualche

0.74

Activations Density 0.263%

phrases indicating uncertainty or conditions related to certain situations or attributes

No Comments

No Known Activations