INDEX

Explanations

beginning markers indicating the start of a significant section or new content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

<",

-0.59

χν

-0.57

IsInitialized

-0.54

 Chry

-0.53

жливо

-0.53

 Maren

-0.52

begin

-0.51

--->

-0.50

τεί

-0.50

eddah

-0.49

POSITIVE LOGITS

<sup>

1.08

ValueStyle

1.02

enumi

0.85

0.80

enumii

0.78

ConstraintMaker

0.75

 ویکی‌پدیا

0.73

^{

0.73

 beginnetje

0.72

BeginContext

0.72

Activations Density 0.021%

beginning markers indicating the start of a significant section or new content

No Comments

No Known Activations