INDEX

Explanations

words related to app reviews, software, and search engine optimization

oai_token-act-pair · 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

 pleaſure

-0.71

 reaſon

-0.68

 purpoſe

-0.66

 Jefus

-0.65

SerializedSize

-0.65

 itſelf

-0.61

 ſtate

-0.61

inghouse

-0.61

 protoimpl

-0.60

 fumée

-0.60

POSITIVE LOGITS

<bos>

1.01

igshid

0.66

 تانيه

0.60

+#+#

0.55

 cherchés

0.51

‌است

0.50

printStackTrace

0.49

ArgsConstructor

0.48

Activations Density 89.791%

words related to app reviews, software, and search engine optimization

No Comments

No Known Activations