INDEX

Explanations

emphatic demonstrative terms and pronouns indicating notable points or findings

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

mekte

-0.47

ht

-0.45

big

-0.45

dziew

-0.43

aus

-0.43

 appartiennent

-0.42

max

-0.42

sa

-0.42

man

-0.41

Max

-0.41

POSITIVE LOGITS

 للمعارف

1.08

脚注の使い方

1.06

ագրություններ

1.02

InSection

0.96

iettivo

0.93

日閲覧

0.92

^(@)

0.90

CppCodeGen

0.90

)‏

0.89

endphp

0.85

Activations Density 0.286%

emphatic demonstrative terms and pronouns indicating notable points or findings

No Comments

No Known Activations