INDEX

Explanations

text where multiple people or groups of people are mentioned together.

oai_token-act-pair · gemini-2.0-flash

similarities

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

ex

-0.48

Ex

-0.45

 فريبيس

-0.45

تحميل

-0.41

herty

-0.40

úly

-0.40

ayaquil

-0.40

oules

-0.40

poj

-0.39

EX

-0.38

POSITIVE LOGITS

rungsseite

0.93

tagHelperRunner

0.83

CloseOperation

0.77

 linkovi

0.76

oredCriteria

0.69

曖昧さ回避

0.69

AutoScale

0.68

 consultato

0.68

 تضيفلها

0.68

igshid

0.68

Activations Density 19.602%

text where multiple people or groups of people are mentioned together.

similarities

No Comments

No Known Activations