INDEX

Explanations

repeated references to the pronoun "it" in various contexts

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

Followed by a preposition or adverb

np_acts-logits-general · gemini-2.0-flash

it followed by a verb or adjective

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.65

 dazu

-0.61

utnik

-0.60

 dafür

-0.59

'],$

-0.59

îtra

-0.59

gecko

-0.58

bitField

-0.57

)‏

-0.57

tue

-0.57

POSITIVE LOGITS

Personensuche

0.55

 Biôgrafia

0.54

 tartalomajánló

0.53

 EconPapers

0.52

曖昧さ回避

0.52

Autoritní

0.52

 beant

0.49

Diweddarwch

0.45

styleable

0.45

Embeddable

0.45

Activations Density 0.165%

repeated references to the pronoun "it" in various contexts

Followed by a preposition or adverb

it followed by a verb or adjective

No Comments

No Known Activations