INDEX

Explanations

phrases related to product features and customer needs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

contentLoaded

-0.77

Bioaccumulative

-0.74

thentic

-0.67

出版年

-0.66

mergeFrom

-0.65

__":

-0.64

LEEP

-0.63

 ujednoznacz

-0.63

phate

-0.63

Попис

-0.62

POSITIVE LOGITS

ActionCreators

0.52

://

0.49

 gradova

0.47

ResumeLayout

0.47

 Wärme

0.41

נטרנט

0.41

 viewDidLoad

0.40

 gambe

0.40

 skriv

0.40

styleUrls

0.39

Activations Density 0.075%

phrases related to product features and customer needs

No Comments

No Known Activations