INDEX

Explanations

words in the context of references and statements about things or people

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

évaluateur

-0.80

 cdti

-0.74

 AppColors

-0.69

 referenties

-0.67

 NDEBUG

-0.67

RouterModule

-0.65

 <=",

-0.64

Controllo

-0.64

 Majefty

-0.63

 Wikimedijinoj

-0.61

POSITIVE LOGITS

requireNonNull

0.63

 where

0.61

OMES

0.58

蔽

0.58

Thats

0.58

why

0.55

 Blumen

0.55

 kiện

0.55

ATS

0.55

б

0.55

Activations Density 0.103%

words in the context of references and statements about things or people

No Comments

No Known Activations