INDEX

Explanations

references to updates or changes in various contexts

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

the word "update"

np_acts-logits-general · gemini-2.0-flash

update

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MLLoader

-0.51

-0.48

ようになる

-0.47

ered

-0.43

ようになった

-0.43

Pozri

-0.43

Identyfik

-0.42

ようになって

-0.42

 vela

-0.42

er

-0.42

POSITIVE LOGITS

 nakalista

0.82

mybatisplus

0.80

 EconPapers

0.78

 updateUser

0.78

 firmware

0.76

OrCreate

0.73

 Updates

0.73

UIControlState

0.71

 updater

0.71

basicConfig

0.70

Activations Density 0.141%

references to updates or changes in various contexts

the word "update"

update

No Comments

No Known Activations