INDEX

Explanations

instances of the word "of," particularly in high frequency or significant contexts

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

存于互联网档案馆

-0.65

∛

-0.63

SpringBootTest

-0.62

ICALS

-0.60

nipeg

-0.56

occasione

-0.56

 chi̍t

-0.56

ordering

-0.56

erial

-0.56

hassee

-0.56

POSITIVE LOGITS

 accumulation

0.61

Url

0.61

 Accumulation

0.60

mybatisplus

0.60

Amy

0.59

 nakalista

0.57

*)(

0.56

Amy

0.55

figsize

0.54

 TabLayout

0.53

Activations Density 0.090%

instances of the word "of," particularly in high frequency or significant contexts

No Comments

No Known Activations