INDEX

Explanations

information related to schemas and database architectures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Datuak

-1.07

enumi

-0.90

 Савезне

-0.88

 <<<<<<<<<<<<<<

-0.82

igshid

-0.81

 EnglishChoose

-0.81

providedIn

-0.80

WaitGroup

-0.79

تقاوى

-0.77

AutoScaleMode

-0.77

POSITIVE LOGITS

他にも

0.68

その他

0.65

Other

0.63

 Other

0.61

ほか

0.60

 lastly

0.60

另外

0.60

 inoltre

0.58

}{*}{

0.57

此外

0.57

Activations Density 0.119%

information related to schemas and database architectures

No Comments

No Known Activations