INDEX

Explanations

phrases indicating realization or revelation

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

PreferredItem

-0.62

dymyr

-0.60

rsiniz

-0.56

DispatchToProps

-0.54

Dichlorobenzene

-0.52

kheim

-0.50

CONSIN

-0.50

kolwiek

-0.49

BeginContext

-0.47

diali

-0.47

POSITIVE LOGITS

Apparently

1.04

 Apparently

1.01

 Evidently

0.99

apparently

0.94

 apparently

0.91

 evidently

0.87

 שוליים

0.81

webElementXpaths

0.75

Evid

0.71

 blijkt

0.70

Activations Density 0.191%

phrases indicating realization or revelation

No Comments

No Known Activations