INDEX

Explanations

terms related to collective knowledge and experiences

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

"To our/my" introducing a statement

np_acts-logits-general · gemini-2.0-flash

to our knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 MonoBehaviour

-0.53

 bağlantılar

-0.52

ukunft

-0.50

 laikā

-0.49

<bos>

-0.49

 Grundlage

-0.48

在一起

-0.47

 together

-0.47

instancetype

-0.46

něte

-0.46

POSITIVE LOGITS

 extent

0.94

rungsseite

0.91

 detriment

0.87

 CreateTagHelper

0.86

 chagrin

0.79

 ול

0.78

 fullest

0.76

Bioaccumulative

0.72

 المعيارى

0.70

ConstraintMaker

0.69

Activations Density 0.265%

terms related to collective knowledge and experiences

"To our/my" introducing a statement

to our knowledge

No Comments

No Known Activations