INDEX

Explanations

instances of introductory words and phrases that signal transitions or additions in text

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

Following an initial word or number

np_acts-logits-general · gemini-2.0-flash

sentence beginnings

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

 propOrder

-1.18

 lenker

-0.97

jooq

-0.97

omock

-0.97

الدراسه

-0.94

GEBURTSDATUM

-0.92

 betweenstory

-0.88

Cyfeiriadau

-0.87

новниш

-0.86

 nakalista

-0.86

POSITIVE LOGITS

さて

0.58

Finally

0.57

................

0.56

Also

0.55

Another

0.53

<eos>

0.52

Lastly

0.52

Anyway

0.51

0.50

autre

0.50

Activations Density 0.849%

instances of introductory words and phrases that signal transitions or additions in text

Following an initial word or number

sentence beginnings

No Comments

No Known Activations