INDEX

Explanations

mentions of restaurants and related dining concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Picchu

-0.86

eol

-0.76

렵

-0.72

 Keim

-0.71

'));

-0.70

'',

-0.70

 fuite

-0.68

Leary

-0.67

 preuves

-0.67

 médec

-0.67

POSITIVE LOGITS

 restaurant

2.08

 restaurants

2.03

 Restaurant

1.90

 Restaurants

1.78

 RESTAURANT

1.71

Restaurant

1.68

restaurant

1.64

Restaurants

1.56

 restaurante

1.55

restaurants

1.52

Activations Density 0.075%

mentions of restaurants and related dining concepts

No Comments

No Known Activations