INDEX

Explanations

words and phrases related to business, computing, government, law, medicine, and/or mathematics.

oai_token-act-pair · gemini-2.0-flash

words related to change and improvement

np_token-act-pair-logits · gpt-4o-mini

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 snippetHide

-0.67

 الرياضيه

-0.66

yeur

-0.64

 otomatig

-0.61

makeText

-0.61

HtmlAttribute

-0.61

expandindo

-0.61

مصادر

-0.61

TagHelpers

-0.60

تقاوى

-0.59

POSITIVE LOGITS

to

0.64

âce

0.46

 Créez

0.45

 slightly

0.44

off

0.41

 back

0.41

ükemmel

0.41

hlen

0.40

 away

0.40

colha

0.40

Activations Density 36.965%

words and phrases related to business, computing, government, law, medicine, and/or mathematics.

words related to change and improvement

No Comments

No Known Activations