INDEX

Explanations

terms related to cooking and recipes

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

 piti

-0.49

 Princip

-0.46

 thống

-0.44

cism

-0.43

啕

-0.43

 AppCompatTheme

-0.43

indt

-0.42

ESTO

-0.41

]').

-0.41

Ừ

-0.41

POSITIVE LOGITS

 vapeur

0.70

BagLayout

0.68

reportWebVitals

0.67

CrossRef

0.66

CardHeader

0.65

ioutil

0.61

Viited

0.61

 Cooks

0.60

COOK

0.60

 blanda

0.60

Activations Density 0.108%

terms related to cooking and recipes

No Comments

No Known Activations