INDEX

Explanations

expressions of agreement and affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Udo

-0.56

expandindo

-0.54

 Kand

-0.51

Udo

-0.50

Bata

-0.49

 कैसी

-0.49

 Bakker

-0.48

atel

-0.48

Kand

-0.48

osan

-0.47

POSITIVE LOGITS

MessageTagHelper

0.85

DataAnnotations

0.67

 thèse

0.61

ArgsConstructor

0.59

 AppDelegate

0.59

viewDidLoad

0.56

 comments

0.56

 scold

0.56

AddColumn

0.56

Życiorys

0.55

Activations Density 0.287%

expressions of agreement and affirmation

No Comments

No Known Activations