INDEX

Explanations

phrases related to safety and health-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mergeFrom

-0.66

makeConstraints

-0.65

 دیکھیے

-0.64

WebElementEntity

-0.63

↹

-0.62

Expedia

-0.61

 ModelExpression

-0.61

 تضيفلها

-0.60

]))

-0.60

脚注の使い方

-0.59

POSITIVE LOGITS

phic

0.51

 Guerra

0.48

+#+#

0.47

ANZA

0.46

 provisions

0.45

displaystyle

0.45

üli

0.44

 Somewhere

0.43

溯

0.43

cape

0.43

Activations Density 1.180%

phrases related to safety and health-related terminology

No Comments

No Known Activations