INDEX

Explanations

phrases indicating components of various subjects or processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

Not in Any Lists

No Comments

Negative Logits

__':

-0.95

 Roskov

-0.90

 NSCoder

-0.89

 ainfi

-0.88

__':

-0.88

tableFuture

-0.85

XmlAccessorType

-0.84

 EnglishChoose

-0.79

OGND

-0.78

 déchir

-0.77

POSITIVE LOGITS

aim

0.56

‘

0.53

0.50

“

0.49

0.48

 high

0.47

aim

0.46

 using

0.45

Activations Density 0.181%

phrases indicating components of various subjects or processes

No Comments

No Known Activations