INDEX

Explanations

references to anti-inflammatory and anti-cancer substances or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 cirrhosis

-0.60

gameserver

-0.57

ArgsConstructor

-0.53

getMinutes

-0.52

 NDEBUG

-0.51

 Мексичка

-0.51

enumi

-0.50

 Baillargeon

-0.49

 occipital

-0.49

 ganglia

-0.49

POSITIVE LOGITS

lipop

0.62

ery

0.60

urate

0.57

oste

0.56

glomer

0.55

antine

0.55

Kdo

0.52

ather

0.52

🧪

0.51

hemat

0.51

Activations Density 3.134%

references to anti-inflammatory and anti-cancer substances or effects

No Comments

No Known Activations