INDEX

Explanations

conversational phrases that indicate uncertainty or inquiry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Page

-0.67

気で

-0.59

`,

-0.55

りましたが

-0.53

øj

-0.53

mayı

-0.53

Page

-0.53

 közel

-0.53

ListTile

-0.53

acağı

-0.52

POSITIVE LOGITS

henswürdigkeiten

0.78

 Retriever

0.78

 Wiktionnaire

0.71

enumi

0.71

 <<<<<<<<<<<<<<

0.69

MemoryWarning

0.68

NameInMap

0.68

ulitis

0.66

afficheront

0.65

する

0.65

Activations Density 0.066%

conversational phrases that indicate uncertainty or inquiry

No Comments

No Known Activations