INDEX

Explanations

words with specific suffixes, particularly "-ly" and sometimes "-al"

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

 समीक्षाओं

-0.64

jspx

-0.62

 CURLOPT

-0.60

">//

-0.60

 onAnimation

-0.59

CloseOperation

-0.58

protoimpl

-0.58

pement

-0.56

///</

-0.55

scriptId

-0.54

POSITIVE LOGITS

Efq

0.52

praš

0.47

cticut

0.44

جغرافيا

0.44

olesale

0.44

UpInside

0.43

原始内容存档于

0.42

SuccessListener

0.42

felves

0.41

 محفوظة

0.41

Activations Density 12.985%

words with specific suffixes, particularly "-ly" and sometimes "-al"

No Comments

No Known Activations