INDEX

Explanations

terms related to system security permissions and exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tartalomajánló

-0.68

 سكانية

-0.66

 ویکی‌آمباردا

-0.64

 CreateTagHelper

-0.62

Slf

-0.62

 الرخصة

-0.59

 Jazeera

-0.58

ellemző

-0.56

انجليز

-0.56

liferay

-0.55

POSITIVE LOGITS

TypedDataSet

1.14

CodeAttribute

1.00

 QtCore

0.60

 purpoſe

0.55

 pleaſure

0.53

enderror

0.52

 Roskov

0.51

 ſta

0.51

BarStyle

0.51

"?>

0.50

Activations Density 0.025%

terms related to system security permissions and exceptions

No Comments

No Known Activations