INDEX

Explanations

elements that indicate a specific scientific or technical concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 soins

-0.59

MessageOf

-0.55

 soin

-0.49

 correctes

-0.49

脚注の使い方

-0.49

Carreira

-0.47

hern

-0.47

IsContent

-0.47

انة

-0.46

 Вікі

-0.46

POSITIVE LOGITS

findpost

0.64

SequentialGroup

0.56

はじめに

0.53

 onAnimation

0.53

waitKey

0.52

 незавершена

0.50

HomeAsUpEnabled

0.50

 aDecoder

0.50

 itſelf

0.49

 صوتيه

0.49

Activations Density 0.936%

elements that indicate a specific scientific or technical concept

No Comments

No Known Activations