INDEX

Explanations

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Савезне

-0.67

 sumpay

-0.62

OGND

-0.61

 мәкал

-0.57

 الحره

-0.56

 كومونز

-0.56

 autorytatywna

-0.54

GEBURTSDATUM

-0.52

 gynhyrchwyd

-0.52

Билгалдахарш

-0.51

POSITIVE LOGITS

biskan

0.36

 Stirn

0.36

interopRequire

0.36

จริงๆ

0.35

 sebenar

0.35

 ModelExpression

0.35

 fapt

0.33

 fact

0.33

 demnach

0.32

aol

0.32

Activations Density 0.183%

the word "that" in various contexts

No Comments

No Known Activations