INDEX

Explanations

terms related to manufacturing processes and product measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

bootstrapcdn

-0.59

parsedMessage

-0.51

UseVisualStyle

-0.49

 TType

-0.49

pup

-0.47

 Meksiku

-0.47

UnitTesting

-0.44

 ListTile

-0.44

MessageOf

-0.44

memberof

-0.42

POSITIVE LOGITS

Statistiche

0.69

annica

0.69

تقاوى

0.67

Numerology

0.64

__(/*!

0.63

 الحره

0.62

"{\

0.62

tvguidetime

0.60

 كومونز

0.60

帖最后由

0.59

Activations Density 1.220%

terms related to manufacturing processes and product measures

No Comments

No Known Activations