INDEX

Explanations

introductory phrases or transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

cimientos

-0.52

 szint

-0.52

enschappen

-0.51

Al

-0.50

 információ

-0.50

ровок

-0.49

脚注の使い方

-0.47

we

-0.47

 azon

-0.46

POSITIVE LOGITS

 contextLoads

0.74

Efq

0.71

 otomatig

0.66

titleMargin

0.65

 Theſe

0.65

 Proced

0.62

ſelf

0.61

 ARXIV

0.61

 Perſ

0.60

ſelves

0.60

Activations Density 0.025%

introductory phrases or transitions

No Comments

No Known Activations