INDEX

Explanations

phrases indicating human interactions and emotional responses

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

"...to do the same" phrase

np_acts-logits-general · gemini-2.0-flash

the same

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

//

-0.66

 通販

-0.59

TargetException

-0.56

ftagPool

-0.54

 createState

-0.52

jspx

-0.52

colha

-0.51

 defaultstate

-0.51

 CascadeType

-0.51

хьтан

-0.50

POSITIVE LOGITS

 same

3.91

same

3.76

Same

3.68

 Same

3.38

 similar

3.32

SAME

2.97

 similarly

2.95

 dezelfde

2.95

 SAME

2.95

similar

2.93

Activations Density 2.516%

phrases indicating human interactions and emotional responses

"...to do the same" phrase

the same

No Comments

No Known Activations