INDEX

Explanations

language about personal relations and disagreements and the topic of discussion

oai_token-act-pair · gemini-2.0-flash

communication

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

 Wiktionnaire

-0.50

 externi

-0.50

ynnwys

-0.45

новниш

-0.44

FailureListener

-0.43

自立

-0.43

kto

-0.41

مراجع

-0.41

хьтан

-0.40

yadh

-0.40

POSITIVE LOGITS

WriteBarrier

0.68

 myſelf

0.64

bior

0.59

."));

0.58

 comigo

0.57

 ProtoMessage

0.56

ValueGenerated

0.56

 lard

0.55

ſelves

0.55

BBM

0.55

Activations Density 0.853%

language about personal relations and disagreements and the topic of discussion

communication

No Comments

No Known Activations