INDEX

Explanations

elements related to summaries or overviews in text

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

 industriale

-0.64

 فريبيس

-0.61

 popolari

-0.60

 NgModule

-0.57

 téléph

-0.56

 Bescheid

-0.55

 colectiva

-0.54

 kysy

-0.54

 credere

-0.54

 Khrushchev

-0.53

POSITIVE LOGITS

تقاوى

0.58

✨:

0.56

InitStruct

0.56

 ویکی‌پدی

0.56

0.54

 "..\..\..\

0.52

</caption>

0.49

 发表于

0.49

WAR

0.49

wari

0.49

Activations Density 0.127%

elements related to summaries or overviews in text

No Comments

No Known Activations