INDEX

Explanations

phrases that describe characteristics and specifications of objects in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 hele

-0.46

 hiç

-0.42

Invoke

-0.42

 vůbec

-0.42

ULAR

-0.41

 aller

-0.41

GO

-0.41

ous

-0.39

ЛЕ

-0.39

POSITIVE LOGITS

 each

1.23

 individually

1.11

EACH

1.08

 Each

1.08

each

1.06

Each

1.04

 EACH

1.03

Chaque

1.00

Efq

0.99

 Majefty

0.97

Activations Density 0.475%

phrases that describe characteristics and specifications of objects in a structured format

No Comments

No Known Activations