INDEX

Explanations

words and phrases related to opinions and suggestions

oai_token-act-pair · gemini-2.0-flash

I/It

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

>{@

-0.49

 ucapnya

-0.47

RegressionTest

-0.46

CopyWith

-0.46

 pungkas

-0.44

énagement

-0.43

лтамалар

-0.43

fe

-0.42

POR

-0.42

pruchs

-0.42

POSITIVE LOGITS

########.

0.69

 Empieza

0.68

 indisponible

0.66

ⓧ

0.63

はじめに

0.63

Autoritní

0.58

UrlResolution

0.57

脚注の使い方

0.56

ohner

0.56

indépendance

0.56

Activations Density 22.203%

words and phrases related to opinions and suggestions

I/It

No Comments

No Known Activations