INDEX

Explanations

references to the past, often using the word "back".

oai_token-act-pair · gemini-2.0-flash

then

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Crossref

-0.68

IGNS

-0.53

virons

-0.50

 Penh

-0.48

Legături

-0.48

LVANIA

-0.47

diğini

-0.47

日閲覧

-0.47

DockStyle

-0.47

zonych

-0.47

POSITIVE LOGITS

 then

2.97

then

2.36

 entonces

2.17

Then

2.16

 Then

2.09

 allora

2.05

 então

2.05

 THEN

2.00

THEN

1.86

 dann

1.65

Activations Density 1.468%

references to the past, often using the word "back".

then

No Comments

No Known Activations