INDEX

Explanations

food-related vocabulary and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 فريبيس

-0.74

GEBURTS

-0.70

GEBURTSDATUM

-0.70

 ولد

-0.55

principalTable

-0.54

出版年

-0.53

photobucket

-0.53

раздо

-0.52

 Chwiliwch

-0.52

 otomatig

-0.52

POSITIVE LOGITS

 taste

2.57

 tastes

2.36

 tasted

2.19

 flavor

2.10

taste

2.07

 Taste

2.01

 tasting

2.00

 flavour

1.98

 flavors

1.96

Taste

1.93

Activations Density 0.227%

food-related vocabulary and expressions

No Comments

No Known Activations