INDEX

Explanations

expressions related to the concept of "things" and their various states or changes

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

"Things" followed by a verb

np_acts-logits-general · gemini-2.0-flash

things are

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

зой

-0.44

-0.43

am

-0.42

par

-0.42

 essa

-0.42

 covering

-0.42

phorus

-0.42

surveys

-0.42

-0.41

-0.40

POSITIVE LOGITS

 ModelExpression

1.07

 متعلقه

1.02

expandindo

0.99

 CreateTagHelper

0.97

LookAnd

0.93

SourceChecksum

0.90

ollectionView

0.87

 Roskov

0.85

Portale

0.83

 Biôgrafia

0.82

Activations Density 0.161%

expressions related to the concept of "things" and their various states or changes

"Things" followed by a verb

things are

No Comments

No Known Activations