INDEX

Explanations

numerical values and references to scientific measurements

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

mybatisplus

-0.87

WaitGroup

-0.84

 FetchType

-0.80

amaño

-0.71

StandardCharsets

-0.71

phosa

-0.70

 TreeSet

-0.69

 թվական

-0.67

thschild

-0.65

 المعيارى

-0.65

POSITIVE LOGITS

The

0.64

 '*')

0.57

 himo

0.57

 ""))

0.52

AccessorTable

0.51

''

0.50

The

0.50

 ''),

0.49

 ""),

0.48

力的

0.48

Activations Density 0.084%

numerical values and references to scientific measurements

No Comments

No Known Activations