INDEX

Explanations

phrases that involve the use of the word "a" or "an" 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ainfi

-0.77

 voorbij

-0.75

 zelve

-0.74

 feroit

-0.72

 pouvoit

-0.72

 zoude

-0.72

Datuak

-0.72

 nuages

-0.70

/******/

-0.69

 popoli

-0.68

POSITIVE LOGITS

有一個

0.74

有一个

0.68

had

0.66

got

0.66

有个

0.65

 have

0.65

 tiene

0.65

 tienes

0.64

 tenido

0.61

 tienen

0.60

Activations Density 0.180%

phrases that involve the use of the word "a" or "an" in various contexts

No Comments

No Known Activations