INDEX

Explanations

expressions of gratitude

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

 يتيمه

-0.81

-0.76

 prolly

-0.70

 Camus

-0.69

 hoga

-0.68

حياته

-0.68

حياتها

-0.67

juz

-0.67

 Hues

-0.67

 mers

-0.64

POSITIVE LOGITS

 Thank

1.61

 thank

1.60

Thank

1.52

thank

1.42

 THANK

1.31

THANK

1.23

kyou

1.12

 thanking

0.98

Thankyou

0.96

 thanked

0.94

Activations Density 0.048%

expressions of gratitude

No Comments

No Known Activations