INDEX

Explanations

references to large or gigantic objects or concepts

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

describing large size

np_acts-logits-general · gemini-2.0-flash

giant or synonyms, followed by nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Aiheesta

-0.50

AxisAlignment

-0.43

ⓧ

-0.42

 怎样

-0.42

PMailer

-0.41

Sci

-0.40

 MaterialApp

-0.40

Roses

-0.39

 Spring

-0.39

 FetchType

-0.39

POSITIVE LOGITS

 giant

1.78

giant

1.62

 gigantic

1.61

Giant

1.49

 Giant

1.48

 gigantes

1.47

 huge

1.42

 Huge

1.41

 giants

1.40

 massive

1.39

Activations Density 0.227%

references to large or gigantic objects or concepts

describing large size

giant or synonyms, followed by nouns

No Comments

No Known Activations