INDEX

Explanations

instances of the word "the"

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

"the" preceding a location or entity

np_acts-logits-general · gemini-2.0-flash

the [entity/place]

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

styleable

-0.59

InjectAttribute

-0.55

 invokingState

-0.52

'][]

-0.52

penup

-0.50

actylus

-0.50

featureID

-0.49

LayoutConstraint

-0.49

mopol

-0.47

 dirig

-0.47

POSITIVE LOGITS

 country

0.72

 electorate

0.64

 للمعارف

0.62

yntaxException

0.61

PyExc

0.59

 OFDb

0.57

 nation

0.56

PRNewswire

0.56

 economy

0.56

OrNil

0.56

Activations Density 0.482%

instances of the word "the"

"the" preceding a location or entity

the [entity/place]

No Comments

No Known Activations