INDEX

Explanations

terms related to naming or labeling something

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

Follows tokens like "called," "dubbed," "named," or "titled"

np_acts-logits-general · gemini-2.0-flash

introducing a name or label

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 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

 myſelf

-0.78

 ſche

-0.76

 Majefty

-0.75

 juſ

-0.75

 itſelf

-0.75

 ſeveral

-0.73

 raiſ

-0.71

 poffible

-0.70

出版年

-0.68

 Reſ

-0.68

POSITIVE LOGITS

 simply

1.25

‘

1.22

1.11

simply

0.99

 appunto

0.99

“

0.98

 simplesmente

0.98

0.96

«

0.95

 semplicemente

0.92

Activations Density 0.330%

terms related to naming or labeling something

Follows tokens like "called," "dubbed," "named," or "titled"

introducing a name or label

No Comments

No Known Activations