INDEX

Explanations

questions starting with "How"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 сайті

-0.50

 себе

-0.49

rouille

-0.47

 snippetHide

-0.47

 فهرست

-0.47

 emberek

-0.47

interface

-0.45

니까

-0.45

fond

-0.45

apd

-0.45

POSITIVE LOGITS

how

1.49

how

1.38

How

1.35

HOW

1.23

HOW

1.20

How

1.17

jak

1.01

wie

0.99

Wie

0.93

 كيف

0.93

Activations Density 0.153%

questions starting with "How"

No Comments

No Known Activations