INDEX

Explanations

references to the word "who" in various contexts

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

those who

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 irgend

-0.35

 interrump

-0.34

 लग

-0.34

phazard

-0.33

 irgende

-0.32

 thereupon

-0.32

 umge

-0.30

তথ্যসূত্র

-0.30

 asomb

-0.30

 start

-0.29

POSITIVE LOGITS

 Ceux

0.73

 Савезне

0.65

 Seeder

0.62

iconque

0.58

########.

0.56

argout

0.56

 którzy

0.56

󠁴

0.56

 onOptions

0.56

 ceux

0.54

Activations Density 0.011%

references to the word "who" in various contexts

those who

No Comments

No Known Activations

references to the word "who" in various contexts

those who

No Comments

No Known Activations