INDEX

Explanations

references to the word "the."

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

"the" preceding nouns

np_acts-logits-general · gemini-2.0-flash

the followed by specific noun

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

use

-0.60

 aspects

-0.58

 aéreo

-0.58

的做法

-0.58

 version

-0.55

 aspect

-0.54

 Spuren

-0.54

aspects

-0.54

 dàng

-0.53

use

-0.53

POSITIVE LOGITS

ThroughAttribute

0.75

 yore

0.74

WebControls

0.67

évaluateur

0.65

setVerticalGroup

0.63

ESSIONAL

0.61

 preceding

0.61

NUMX

0.61

 contextLoads

0.60

endpush

0.59

Activations Density 0.713%

references to the word "the."

"the" preceding nouns

the followed by specific noun

No Comments

No Known Activations