INDEX

Explanations

references to specific locations or geographical names

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

={({

-0.49

SequentialGroup

-0.45

createClass

-0.45

írus

-0.42

 Viro

-0.40

ContextHolder

-0.40

 <=",

-0.40

conform

-0.39

ihnachten

-0.39

 Sono

-0.39

POSITIVE LOGITS

ValueStyle

0.71

 stomach

0.69

 blade

0.64

 Stomach

0.63

 ویکی‌پدی

0.62

pagination

0.57

 Orchestra

0.56

VersionUID

0.56

 Stadium

0.55

 marathon

0.55

Activations Density 0.287%

references to specific locations or geographical names

No Known Activations