INDEX

Explanations

terms related to "dia," indicating a focus on certain categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 doubtnut

-0.82

 pleaſure

-0.82

 purpoſe

-0.80

 Jefus

-0.79

 Majefty

-0.79

 myſelf

-0.76

 Anſ

-0.75

出版年

-0.71

 quæ

-0.70

 cristi

-0.69

POSITIVE LOGITS

dia

0.84

dia

0.71

Vo

0.58

 vast

0.57

gar

0.57

Dia

0.57

vo

0.56

словно

0.54

 día

0.53

 general

0.53

Activations Density 0.090%

terms related to "dia," indicating a focus on certain categories or classifications

No Comments

No Known Activations