INDEX

Explanations

references to characters and storytelling elements from specific media or narratives

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

preceding parenthetical phrases and other punctuation

np_acts-logits-general · gemini-2.0-flash

year, queen, deletion, incident, USA

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

WaitGroup

-0.61

)»

-0.58

HandlerContext

-0.55

 autorytatywna

-0.55

municipi

-0.54

 Huxley

-0.52

 كومونز

-0.51

ioutil

-0.51

SaveSave

-0.50

();)

-0.50

POSITIVE LOGITS

 nakalista

0.59

plus

0.53

 plus

0.50

 pasted

0.50

frontmatter

0.49

Plus

0.49

MessageOf

0.47

 displayed

0.47

 overlaid

0.46

 republiky

0.46

Activations Density 0.822%

references to characters and storytelling elements from specific media or narratives

preceding parenthetical phrases and other punctuation

year, queen, deletion, incident, USA

No Comments

No Known Activations