INDEX

Explanations

language that indicates a personal perspective or opinion

oai_token-act-pair · gemini-2.0-flash

opinions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 financieras

-0.46

hawa

-0.44

 Common

-0.44

 financières

-0.43

Common

-0.43

APON

-0.43

 degrés

-0.41

ilyen

-0.40

 financieros

-0.40

 будто

-0.40

POSITIVE LOGITS

<bos>

1.17

 myſelf

1.05

 itſelf

1.02

 himſelf

0.94

ſelf

0.91

 Monfieur

0.90

 Theſe

0.89

 themſelves

0.88

OGND

0.87

 Majefty

0.86

Activations Density 2.517%

language that indicates a personal perspective or opinion

opinions

No Comments

No Known Activations