INDEX

Explanations

proper nouns and some articles/pronouns in various contexts

oai_token-act-pair · gemini-2.0-flash

Names and stories

np_max-act · 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

IFrame

Link

Negative Logits

RegressionTest

-0.62

 propOrder

-0.59

principalTable

-0.55

igshid

-0.54

ьаж

-0.53

])));

-0.52

ScreenState

-0.52

 autorytatywna

-0.51

तिहास

-0.50

 BorderRadius

-0.50

POSITIVE LOGITS

TargetException

0.51

 fhew

0.50

WARDS

0.50

 trade

0.50

cần

0.49

:+:

0.47

ędzynarod

0.47

atuor

0.45

 pleaſure

0.45

 thiệu

0.44

Activations Density 4.770%

proper nouns and some articles/pronouns in various contexts

Names and stories

No Known Activations