INDEX

Explanations

references to food preparation and culinary details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Autoritní

-0.69

ագրություններ

-0.60

 Filled

-0.53

 travailleurs

-0.52

 hasard

-0.50

abestanden

-0.50

 nød

-0.50

dova

-0.49

ferenz

-0.49

ophila

-0.48

POSITIVE LOGITS

 steak

0.97

 steaks

0.96

steak

0.92

 Steak

0.83

Steak

0.82

 burger

0.65

 sear

0.64

 ステーキ

0.63

🥩

0.63

 fries

0.62

Activations Density 0.073%

references to food preparation and culinary details

No Comments

No Known Activations