INDEX

Explanations

first-person perspective expressions and personal reflections

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

"I think" or personal opinions

np_acts-logits-general · gemini-2.0-flash

i think, i notice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 occasioned

-0.67

rxjs

-0.59

 sundry

-0.59

cassert

-0.58

 aegis

-0.58

 thence

-0.57

 confound

-0.57

 bedrock

-0.56

 capricious

-0.56

 extant

-0.55

POSITIVE LOGITS

Personensuche

0.75

 personally

0.70

 continuously

0.66

 unfortunately

0.66

 truly

0.61

 atleast

0.60

жели

0.59

 constantemente

0.58

不断的

0.58

 malheureusement

0.58

Activations Density 0.176%

first-person perspective expressions and personal reflections

"I think" or personal opinions

i think, i notice

No Comments

No Known Activations