INDEX

Explanations

keywords and phrases relevant to research studies and analyses, particularly in scientific literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 myſelf

-0.81

 Monfieur

-0.79

 Majefty

-0.78

 himſelf

-0.76

 Theſe

-0.74

 ―――――

-0.70

ünst

-0.69

 houſe

-0.67

StoryboardSegue

-0.67

Efq

-0.67

POSITIVE LOGITS

 what

0.59

how

0.55

an

0.53

0.48

 prů

0.48

 Part

0.48

“

0.48

一种

0.47

what

0.47

/***/

0.47

Activations Density 0.221%

keywords and phrases relevant to research studies and analyses, particularly in scientific literature

No Comments

No Known Activations