INDEX

Explanations

words specifically related to 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 croy

-0.80

'));

-0.77

()));

-0.75

Leary

-0.75

ơn

-0.75

])[

-0.73

렵

-0.72

'',

-0.72

 Keim

-0.72

Jof

-0.71

POSITIVE LOGITS

 restaurant

1.84

 restaurants

1.75

 Restaurant

1.56

 Restaurants

1.47

Restaurant

1.41

restaurant

1.39

 RESTAURANT

1.34

Restaurants

1.33

 restaurante

1.24

restaurants

1.23

Activations Density 0.034%

words specifically related to restaurants and dining establishments

No Comments

No Known Activations