INDEX

Explanations

proper nouns, particularly names of institutions and publishers

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

 OnTriggerEnter

-0.63

Spoljašnje

-0.57

 ComVisible

-0.56

 paramInt

-0.51

来

-0.50

"?

-0.50

rungsseite

-0.47

BaseController

-0.47

nicamente

-0.46

 breaking

-0.46

POSITIVE LOGITS

RRect

0.62

getClassLoader

0.61

ंदीखरीदारी

0.58

cademic

0.57

المناصب

0.56

 通販

0.55

ValueStyle

0.55

addPreferredGap

0.54

KeyId

0.54

 Roskov

0.54

Activations Density 0.170%

proper nouns, particularly names of institutions and publishers

No Comments

No Known Activations