INDEX

Explanations

expressions of positive or negative expectations regarding outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 contextLoads

-0.67

HtmlAttribute

-0.62

OuterClass

-0.58

monių

-0.57

liferay

-0.53

richTextPanel

-0.53

/\.

-0.53

 leçon

-0.52

 houſe

-0.51

lisle

-0.51

POSITIVE LOGITS

ंदीखरीदारी

0.57

 BoxDecoration

0.52

 JpaRepository

0.51

coltura

0.50

ylem

0.49

 wäre

0.49

UseVisualStyle

0.48

 TextAppearance

0.48

ClientSize

0.47

туга

0.47

Activations Density 0.241%

expressions of positive or negative expectations regarding outcomes

No Comments

No Known Activations