INDEX

Explanations

contrastive phrases indicating differences or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Patton

-0.68

 Maynard

-0.64

 Coates

-0.63

 daly

-0.57

bakken

-0.57

̯

-0.57

ServiceImpl

-0.56

 Daly

-0.56

componentDid

-0.56

-0.55

POSITIVE LOGITS

 whereas

2.24

 Whereas

2.20

Whereas

2.19

whereas

2.13

 WHEREAS

1.24

WHEREAS

0.98

webElementXpaths

0.96

 sedangkan

0.94

 Versus

0.89

 Sedangkan

0.89

Activations Density 0.125%

contrastive phrases indicating differences or comparisons

No Comments

No Known Activations