INDEX

Explanations

occurrences and variations of the word "it"

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

"it" at the beginning of sentences

np_acts-logits-general · gemini-2.0-flash

it following words like `is`, `in`, `all`

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

 Schreiber

-0.62

서는

-0.58

ombre

-0.56

haj

-0.55

ULATE

-0.54

ENTE

-0.54

тельность

-0.53

Meno

-0.52

 Mestre

-0.52

 Tobin

-0.52

POSITIVE LOGITS

QMetaType

0.69

__":

0.68

EndGlobalSection

0.67

 rains

0.65

 فريبيس

0.65

OGND

0.65

 autorytatywna

0.64

principalTable

0.63

AsUp

0.62

+#+#

0.60

Activations Density 0.404%

occurrences and variations of the word "it"

"it" at the beginning of sentences

it following words like `is`, `in`, `all`

No Comments

No Known Activations