INDEX

Explanations

phrases that express conversational transitions or affirmations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Roskov

-0.94

IsContent

-0.80

 saites

-0.76

TagMode

-0.73

epa

-0.69

 الحره

-0.67

abyrinth

-0.66

homonymie

-0.65

 MessageBoxIcon

-0.65

Personensuche

-0.65

POSITIVE LOGITS

 Well

1.12

Well

1.04

 well

0.80

 WELL

0.76

well

0.73

 yeah

0.72

hey

0.72

Welp

0.69

 Pues

0.67

 Ну

0.66

Activations Density 0.056%

phrases that express conversational transitions or affirmations

No Comments

No Known Activations