INDEX

Explanations

words and phrases used in political discourse and news coverage.

oai_token-act-pair · gemini-2.0-flash

movement and force

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

me

-0.55

horabuena

-0.52

 conmigo

-0.49

 miei

-0.48

 mnie

-0.47

Me

-0.46

 lesquels

-0.46

ungguhnya

-0.46

he

-0.44

在我

-0.44

POSITIVE LOGITS

SharedDtor

0.70

 resourceCulture

0.66

}</

0.63

sizeCache

0.63

__(/*!

0.63

 ſame

0.62

 Nehru

0.62

 money

0.62

OrBuilder

0.61

 محفوظة

0.61

Activations Density 10.103%

words and phrases used in political discourse and news coverage.

movement and force

No Comments

No Known Activations