INDEX

Explanations

words and phrases related to negation or cancellation

oai_token-act-pair · gemini-2.0-flash

cancel

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

-0.56

-0.48

fan

-0.47

per

-0.46

la

-0.46

 dividend

-0.44

-0.43

]{\

-0.43

)->

-0.43

BrowserModule

-0.43

POSITIVE LOGITS

 ModelExpression

0.81

Efq

0.77

 doubtnut

0.77

 Theſe

0.76

SequentialGroup

0.76

 leaſt

0.75

 AppColors

0.75

 Monfieur

0.75

ArgsConstructor

0.72

ſelf

0.72

Activations Density 0.545%

words and phrases related to negation or cancellation

cancel

No Comments

No Known Activations