INDEX

Explanations

expressions of curiosity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

eseorang

-0.72

 ſtate

-0.72

 diſt

-0.71

脚注の使い方

-0.70

Efq

-0.70

 myſelf

-0.68

 Monfieur

-0.68

 purpoſe

-0.68

 ainfi

-0.67

verläs

-0.66

POSITIVE LOGITS

 curiosity

1.16

 curious

1.11

curious

0.91

curios

0.88

 Curiosity

0.88

 curios

0.78

SequentialGroup

0.76

 bezeichneter

0.75

 curiosidad

0.73

Curious

0.73

Activations Density 0.131%

expressions of curiosity

No Comments

No Known Activations