INDEX

Explanations

instances of generalizations or overarching statements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 circonst

-0.64

 Glam

-0.54

ilden

-0.54

 nokt

-0.54

 abbigliamento

-0.53

 affari

-0.53

 gewünschten

-0.51

".$_

-0.51

য

-0.50

 Дата

-0.50

POSITIVE LOGITS

はじめに

0.85

culously

0.84

icamente

0.78

ortunadamente

0.74

 оригіналу

0.74

ępnie

0.73

__":

0.72

ditionally

0.72

SequentialGroup

0.72

 تضيفلها

0.70

Activations Density 0.502%

instances of generalizations or overarching statements in the text

No Comments

No Known Activations