INDEX

Explanations

text related to applications and their features

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

np_acts-logits-general · gemini-2.0-flash

ads and advertisements

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

 myſelf

-0.63

 auffi

-0.58

rowable

-0.58

)))));

-0.56

MENAFN

-0.55

 Hift

-0.53

 Wikiseite

-0.52

الحياه

-0.52

 themſelves

-0.52

 faſt

-0.50

POSITIVE LOGITS

ads

1.46

ad

1.27

Ads

1.27

 advertisements

1.27

 advertising

1.21

Ads

1.21

 advertisement

1.17

 adverts

1.16

Ad

1.09

ads

1.08

Activations Density 0.177%

text related to applications and their features

advertisements

ads and advertisements

No Comments

No Known Activations