INDEX

Explanations

positive adjectives and descriptors related to enjoyment and quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

matchCondition

-0.40

Therapie

-0.38

 GIPHY

-0.37

Sied

-0.37

 pans

-0.36

OGND

-0.36

 esfuer

-0.35

IMENTAL

-0.35

 hochzeit

-0.34

 pseudos

-0.34

POSITIVE LOGITS

écou

0.50

 Awesome

0.49

存于互联网档案馆

0.47

jspx

0.47

Aholisi

0.45

 Interesting

0.45

Переваги

0.45

دانشنامهٔ

0.45

TextHelper

0.44

 outstanding

0.42

Activations Density 0.651%

positive adjectives and descriptors related to enjoyment and quality

No Comments

No Known Activations