INDEX

Explanations

instances of the word "is."

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

starting with "is" or containing "Is"

np_acts-logits-general · gemini-2.0-flash

is followed by prefixes or word starts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

CloseOperation

-1.00

oredCriteria

-0.91

AddTagHelper

-0.88

دانشنامهٔ

-0.84

Initialized

-0.83

Valid

-0.80

Empty

-0.80

المناصب

-0.76

 disambiguazione

-0.76

InitVars

-0.74

POSITIVE LOGITS

mIs

0.63

IS

0.54

raeli

0.54

bIs

0.52

thmus

0.51

abelle

0.50

 there

0.48

lamabad

0.48

getIs

0.48

 JpaRepository

0.47

Activations Density 0.162%

instances of the word "is."

starting with "is" or containing "Is"

is followed by prefixes or word starts

No Comments

No Known Activations