INDEX

Explanations

transitional words and phrases that introduce explanations or justifications, particularly those indicating cause and effect or comparison

oai_token-act-pair · gemini-2.0-flash

a variety of seemingly unrelated words

np_token-act-pair-logits · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WriteBarrier

-0.80

windowFixed

-0.74

Ligações

-0.69

Portály

-0.68

/**

-0.66

')):

-0.63

TagHelper

-0.63

')")

-0.62

homonymie

-0.62

endous

-0.62

POSITIVE LOGITS

 chrétien

0.47

 InputDecoration

0.47

assies

0.46

 âmes

0.46

 nessun

0.46

 taches

0.46

 pattes

0.45

 parallèle

0.45

før

0.44

tafogo

0.44

Activations Density 1.413%

transitional words and phrases that introduce explanations or justifications, particularly those indicating cause and effect or comparison

a variety of seemingly unrelated words

to

No Comments

No Known Activations