INDEX

Explanations

phrases discussing government policies or healthcare issues

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

frequently followed by specific prepositions or verbs

np_acts-logits-general · gemini-2.0-flash

always / never

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 potentially

-0.48

 fully

-0.46

 Umständen

-0.45

entially

-0.43

метра

-0.43

 Fully

-0.42

Fully

-0.42

ungkinkan

-0.41

程度上

-0.40

 possibly

-0.39

POSITIVE LOGITS

 always

1.19

always

1.17

siempre

1.12

 everytime

1.09

Always

1.09

 sempre

1.08

sempre

1.08

 alway

1.06

 siempre

1.05

 Always

1.03

Activations Density 0.294%

phrases discussing government policies or healthcare issues

frequently followed by specific prepositions or verbs

always / never

No Comments

No Known Activations