INDEX

Explanations

formal question and answer structures within conversations or inquiries

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 ویکی‌پدیا

-0.60

Efq

-0.59

 betweenstory

-0.58

 épa

-0.52

 Conſ

-0.52

 Arhi

-0.51

 Diſ

-0.50

kyl

-0.50

 Reſ

-0.50

zegor

-0.48

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.62

Answer

0.60

Билгалдахарш

0.59

webElementXpaths

0.59

 answered

0.58

 replied

0.57

migrationBuilder

0.57

 Answer

0.57

 answer

0.55

 reply

0.54

Activations Density 0.057%

formal question and answer structures within conversations or inquiries

No Comments

No Known Activations