INDEX

Explanations

phrases related to grouping and classification in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

psia

-0.45

FullPath

-0.44

 substituted

-0.42

 éditoriale

-0.41

 вот

-0.41

 none

-0.41

leistung

-0.40

OrBuilder

-0.40

BL

-0.40

ži

-0.40

POSITIVE LOGITS

 categories

1.00

fjspx

0.97

 categorized

0.91

 categor

0.91

 classifications

0.90

 categorization

0.87

 categorize

0.86

 classifying

0.84

 classified

0.84

writeFieldEnd

0.84

Activations Density 0.453%

phrases related to grouping and classification in research studies

No Comments

No Known Activations