INDEX

Explanations

conjunctions and logical operators within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 perfección

-0.67

 cielos

-0.63

 illegally

-0.61

 Englishman

-0.60

 bouche

-0.59

 plancher

-0.58

 használat

-0.58

americanos

-0.57

licet

-0.57

 stupidly

-0.57

POSITIVE LOGITS

脚注の使い方

0.73

BufferException

0.69

الحياه

0.66

 AssemblyCulture

0.65

 insight

0.62

LayoutStyle

0.60

躇

0.60

 hữu

0.59

 respons

0.59

 AttributeSet

0.57

Activations Density 0.365%

conjunctions and logical operators within the text

No Comments

No Known Activations