INDEX

Explanations

references to awards and honors

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

Mentions "award" or "awards"

np_acts-logits-general · gemini-2.0-flash

award

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 FetchType

-0.48

wsi

-0.48

-0.47

ghis

-0.46

 mommy

-0.46

cokinetics

-0.45

⊶

-0.44

industan

-0.44

msen

-0.44

 Luci

-0.43

POSITIVE LOGITS

 award

1.23

 Award

1.21

Award

1.03

 Awards

1.02

 AWARD

1.02

 awards

1.00

 awarded

0.94

award

0.93

Awards

0.89

awards

0.86

Activations Density 0.102%

references to awards and honors

Mentions "award" or "awards"

award

No Comments

No Known Activations

references to awards and honors

Mentions "award" or "awards"

award

No Comments

No Known Activations