INDEX

Explanations

expressions and references related to personal experiences and emotional reflections

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

"I" followed by verbs of thought/opinion

np_acts-logits-general · gemini-2.0-flash

I think or wonder

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

kloped

-0.62

 насељу

-0.58

 entirety

-0.54

osv

-0.53

 altezza

-0.52

 duração

-0.52

klart

-0.51

 majorité

-0.51

 şekilde

-0.51

 trás

-0.50

POSITIVE LOGITS

 suspect

0.81

 wonder

0.80

^(@)

0.74

 seldom

0.72

 ་་

0.72

 wondered

0.70

Herzliche

0.68

ofern

0.68

wonder

0.68

 jedenfalls

0.67

Activations Density 0.438%

expressions and references related to personal experiences and emotional reflections

"I" followed by verbs of thought/opinion

I think or wonder

No Comments

No Known Activations