INDEX

Explanations

adverbs indicating degree or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 émotion

-0.65

XmlAccessorType

-0.61

ⓧ

-0.61

 mourut

-0.60

lamó

-0.59

Shows

-0.58

 médicaux

-0.58

 dries

-0.58

Writes

-0.58

 hende

-0.57

POSITIVE LOGITS

częściej

0.83

적으로

0.74

 have

0.73

edly

0.72

ledem

0.68

 kunna

0.67

verläs

0.66

 оригіналу

0.66

 lượt

0.66

 börja

0.65

Activations Density 0.184%

adverbs indicating degree or extent

No Comments

No Known Activations