INDEX

Explanations

questions and prompts for reader engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

utilisons

-0.68

encodeWith

-0.65

 aapt

-0.61

 المعيارى

-0.60

LabelTagHelper

-0.60

UrlResolution

-0.59

 MenuView

-0.58

 wireType

-0.57

 JAXB

-0.57

 '\\;'

-0.55

POSITIVE LOGITS

RenderAtEndOf

0.61

<eos>

0.56

قایناقلار

0.50

__*/

0.48

RegressionTest

0.47

Full

0.46

ivin

0.46

ropical

0.45

setTypeface

0.45

 Full

0.44

Activations Density 0.181%

questions and prompts for reader engagement

No Comments

No Known Activations