INDEX

Explanations

mentions of restaurants and dining establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 croy

-0.79

'',

-0.78

Leary

-0.73

'));

-0.72

Ỹ

-0.71

.*")]

-0.71

%;">

-0.71

skj

-0.70

 auroit

-0.70

 évêque

-0.70

POSITIVE LOGITS

 restaurant

1.31

 restaurants

1.31

 Restaurant

1.16

 Restaurants

1.11

Restaurants

1.01

Restaurant

1.00

 RESTAURANT

0.95

restaurant

0.93

restaurants

0.92

 restaurante

0.85

Activations Density 0.023%

mentions of restaurants and dining establishments

No Comments

No Known Activations